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

    Neuronpedia

    INDEX
    Explanations

    expressions of skepticism or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to skepticism and uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zie
    -0.74
    ibrary
    -0.71
    ramid
    -0.66
    ktop
    -0.63
    emetery
    -0.63
    ĺħ
    -0.62
     Occupations
    -0.61
    ummer
    -0.61
    dos
    -0.60
     redund
    -0.60
    POSITIVE LOGITS
    lessly
    1.44
    worthiness
    1.15
    fully
    1.06
    fulness
    1.05
    lessness
    0.88
    ingly
    0.87
    ful
    0.83
    BLE
    0.80
    lust
    0.80
    bly
    0.79
    Act Density 0.023%

    No Known Activations