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

    Neuronpedia

    INDEX
    Explanations

    instances of intimate physical interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     raiſ
    -0.79
    ſelf
    -0.79
     himſelf
    -0.78
     themſelves
    -0.76
     itſelf
    -0.74
     myſelf
    -0.72
     Anſ
    -0.72
     ſtate
    -0.71
     Monfieur
    -0.71
    neſs
    -0.69
    POSITIVE LOGITS
     الحره
    0.56
     pinulongan
    0.54
    SafeMath
    0.51
    Rüyada
    0.51
     touch
    0.48
     hugged
    0.47
    WebElementEntity
    0.47
    WireFormatLite
    0.47
     kiss
    0.47
    sidemargin
    0.45
    Act Density 0.306%

    No Known Activations