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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe actions or things people are expected to do

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hest
    -0.55
    ="_
    -0.53
    ctivos
    -0.49
     fortfarande
    -0.49
    욱
    -0.47
     dezen
    -0.47
    ting
    -0.47
    ogen
    -0.46
     livré
    -0.46
    üyada
    -0.46
    POSITIVE LOGITS
     للمعارف
    0.82
    principalColumn
    0.76
    HostException
    0.75
    ChildScrollView
    0.74
     الرياضيه
    0.72
    الحياه
    0.69
    InputBorder
    0.69
     itſelf
    0.68
    ruptedException
    0.67
     initComponents
    0.67
    Act Density 0.143%

    No Known Activations