© 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. 1578
    Prev
    Next
    INDEX
    Explanations

    references to military or emergency situations

    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
    姫
    -0.69
    IENCE
    -0.60
    ABLE
    -0.60
     aids
    -0.59
     obedient
    -0.59
    MENT
    -0.57
     ann
    -0.56
     firearm
    -0.55
     cha
    -0.55
     notice
    -0.55
    POSITIVE LOGITS
    eele
    0.80
    insk
    0.79
    osit
    0.74
    ussen
    0.70
    ucket
    0.67
    veyard
    0.66
    lc
    0.65
    agate
    0.64
    let
    0.63
    lets
    0.63
    Activations Density 0.367%

    No Known Activations