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

    Neuronpedia

    INDEX
    Explanations

    adjectives and verbs related to changes or actions

    oai_token-act-pair · gpt-3.5-turbo

    past-tense verbs related to significant actions or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cipled
    -0.76
    arta
    -0.69
    itte
    -0.68
    arger
    -0.65
    oidal
    -0.63
    aging
    -0.63
    PI
    -0.62
    eland
    -0.62
    bid
    -0.61
    coin
    -0.60
    POSITIVE LOGITS
     theirs
    0.71
    ĸļ
    0.69
    hers
    0.69
    nesday
    0.69
    ãĤ¤ãĥĪ
    0.66
    ocument
    0.63
    raints
    0.62
    Ĥİ
    0.61
     upon
    0.60
     itself
    0.59
    Act Density 0.758%

    No Known Activations