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

    Neuronpedia

    INDEX
    Explanations

    dates

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and months mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    licted
    -0.53
     predec
    -0.53
     careless
    -0.52
     streng
    -0.50
     overc
    -0.50
     botched
    -0.49
     cumbers
    -0.49
    elo
    -0.49
     regression
    -0.48
    ettel
    -0.48
    POSITIVE LOGITS
     Madness
    0.84
     29
    0.84
     31
    0.84
     27
    0.82
     28
    0.81
     26
    0.81
     25
    0.79
     22
    0.79
     23
    0.79
     TBA
    0.77
    Act Density 0.088%

    No Known Activations