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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 816
    Prev
    Next
    INDEX
    Explanations

    monetary amounts and fines

    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
    ises
    -0.76
    secure
    -0.70
    REC
    -0.65
    uria
    -0.64
    akers
    -0.61
     workplaces
    -0.60
     careg
    -0.60
    erie
    -0.59
    mination
    -0.59
    alogue
    -0.59
    POSITIVE LOGITS
    ··
    0.86
     €
    0.81
    approximately
    0.80
    .$
    0.73
     $\
    0.71
     ¥
    0.70
     circa
    0.70
    yip
    0.69
     approximately
    0.68
     Mub
    0.68
    Activations Density 0.138%

    No Known Activations