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

    Neuronpedia

    INDEX
    Explanations

    phrases that establish comparisons or descriptions of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     auft
    -0.66
    发表于
    -0.65
    SPATH
    -0.60
     forgets
    -0.59
    assioned
    -0.59
    WriteBarrier
    -0.59
    uhi
    -0.57
    ütün
    -0.57
     vergessen
    -0.56
     Happens
    -0.56
    POSITIVE LOGITS
     being
    0.81
     étant
    0.79
     fiind
    0.76
    expandindo
    0.67
    being
    0.60
     be
    0.59
     part
    0.58
     שוליים
    0.56
     být
    0.56
     likely
    0.56
    Act Density 0.357%

    No Known Activations