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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases related to behavior and treatment in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IsContent
    -0.57
    fillType
    -0.56
     resourceCulture
    -0.56
    utives
    -0.54
     الاطلاع
    -0.53
     يتيمه
    -0.52
    ⓧ
    -0.52
    Personendaten
    -0.51
    IndexPath
    -0.50
     voire
    -0.50
    POSITIVE LOGITS
     differently
    1.41
     according
    1.02
     accordingly
    0.98
     diffé
    0.86
     incorrectly
    0.85
    according
    0.82
     like
    0.79
    differ
    0.75
     how
    0.73
     correctly
    0.72
    Act Density 0.626%

    No Known Activations