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

    Neuronpedia

    INDEX
    Explanations

    times and events related to specific actions or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    specific time-related events or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     streng
    -0.67
     barg
    -0.64
     millenn
    -0.62
    ãĥ³ãĤ¸
    -0.61
     Presbyter
    -0.59
     Slim
    -0.57
     thous
    -0.56
     billionaires
    -0.56
     classy
    -0.56
     Kash
    -0.55
    POSITIVE LOGITS
     onset
    1.08
     unless
    0.96
    uberty
    0.95
    pletion
    0.93
     completion
    0.93
     ().
    0.87
     onwards
    0.85
     whichever
    0.84
    illation
    0.83
     (~
    0.83
    Act Density 0.302%

    No Known Activations