Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that express thought and evaluation regarding societal norms and personal choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Prid
    -0.55
    //
    -0.47
    IGraphics
    -0.47
     vincit
    -0.46
    GraphicsUnit
    -0.45
    ап
    -0.44
     chi̍t
    -0.43
     msglen
    -0.43
    แก้
    -0.43
    roep
    -0.43
    POSITIVE LOGITS
    rungsseite
    0.93
    まさか
    0.74
    didSet
    0.71
     createSlice
    0.64
    HideFlags
    0.62
    madu
    0.59
     flo
    0.58
    featureID
    0.58
     الرياضيه
    0.58
    "]));
    0.57
    Act Density 0.224%

    No Known Activations