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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs and forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     are
    -0.65
     were
    -0.63
     themselves
    -0.62
    들
    -0.58
    šli
    -0.57
    erano
    -0.56
    FieldBuilder
    -0.56
    prefixer
    -0.55
    glGen
    -0.55
    ViewType
    -0.54
    POSITIVE LOGITS
     itſelf
    0.73
     itself
    0.69
     ProtoMessage
    0.69
    itself
    0.66
    
    0.59
     للمعارف
    0.59
    Its
    0.55
    Filmographie
    0.53
    KommentareTeilen
    0.53
     Itself
    0.53
    Act Density 0.144%

    No Known Activations