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

    Neuronpedia

    INDEX
    Explanations

    dates written in the format Month Day

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific dates and related numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Goldstein
    -0.92
     Jill
    -0.83
     Hua
    -0.82
     Cohn
    -0.80
    Lenin
    -0.78
    Wilson
    -0.77
     Hil
    -0.77
     Stella
    -0.76
     ISIL
    -0.75
     Alc
    -0.74
    POSITIVE LOGITS
    4
    1.36
     4
    1.31
    four
    1.02
     Four
    0.96
     four
    0.92
    Fourth
    0.91
    fourth
    0.89
     IV
    0.89
    Four
    0.89
     fourth
    0.86
    Act Density 0.306%

    No Known Activations