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

    Neuronpedia

    INDEX
    Explanations

    intensifiers and adverbs that modify the degree of descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.57
    AnimationsModule
    -0.56
    ectoria
    -0.54
     transfieras
    -0.53
    archiviato
    -0.49
     elég
    -0.49
    ftagPool
    -0.48
     Additional
    -0.48
     ganska
    -0.48
    Additional
    -0.48
    POSITIVE LOGITS
     few
    0.73
     small
    0.66
     short
    0.63
     late
    0.62
     large
    0.62
     recently
    0.60
     soon
    0.60
     young
    0.59
     narrow
    0.59
     recent
    0.59
    Act Density 0.403%

    No Known Activations