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

    Neuronpedia

    INDEX
    Explanations

    phrases related to career and work

    oai_token-act-pair · gpt-3.5-turbo

    phrases that discuss specific topics or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.77
    ega
    -0.73
    soever
    -0.72
    ahu
    -0.71
    §
    -0.70
    ¬¼
    -0.69
    EngineDebug
    -0.68
    rament
    -0.67
     [*
    -0.66
    endo
    -0.66
    POSITIVE LOGITS
     including
    1.19
     namely
    1.16
     culminating
    0.96
     Including
    0.95
     noting
    0.93
    including
    0.91
     includ
    0.91
     comparing
    0.91
     concluding
    0.90
     detailing
    0.89
    Act Density 0.408%

    No Known Activations