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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or roles

    oai_token-act-pair · gpt-3.5-turbo

    actions related to performance and participation in events or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wont
    -0.78
    fortunately
    -0.70
    pmwiki
    -0.67
    icult
    -0.66
     fortunately
    -0.62
     luckily
    -0.61
     valiant
    -0.60
     whim
    -0.59
    abet
    -0.58
    rities
    -0.58
    POSITIVE LOGITS
    enance
    0.90
     him
    0.76
    dress
    0.74
    igate
    0.73
     anew
    0.68
     another
    0.66
     Yiannopoulos
    0.65
     his
    0.62
    clude
    0.62
    ign
    0.60
    Act Density 0.355%

    No Known Activations