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

    Neuronpedia

    INDEX
    Explanations

    actions or transitions

    oai_token-act-pair · gpt-3.5-turbo

    gerunds or participles related to actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pg
    -0.76
    unless
    -0.66
    inho
    -0.64
    *****
    -0.63
     unless
    -0.62
     lineback
    -0.61
    NG
    -0.58
    tu
    -0.57
    if
    -0.57
    ifiable
    -0.56
    POSITIVE LOGITS
     awhile
    0.73
     pains
    0.71
    ©¶æ
    0.70
     unsuccessfully
    0.70
     countless
    0.69
    prus
    0.69
     numerous
    0.67
    undreds
    0.66
     several
    0.66
     Pengu
    0.63
    Act Density 0.144%

    No Known Activations