© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1954
    Prev
    Next
    INDEX
    Explanations

    adjectives related to magnitude or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     acron
    -0.71
    ガ
    -0.70
     traps
    -0.69
    codes
    -0.69
    speak
    -0.69
    �
    -0.68
     encounters
    -0.67
    faces
    -0.67
     IDs
    -0.66
     fronts
    -0.66
    POSITIVE LOGITS
     amount
    1.07
    amount
    0.88
     percentage
    0.87
     number
    0.84
    reciation
    0.82
     proportion
    0.81
     quantity
    0.81
     portion
    0.81
     Amount
    0.78
    ithing
    0.75
    Activations Density 0.111%

    No Known Activations