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

    Neuronpedia

    INDEX
    Explanations

    specific dates and numbers

    oai_token-act-pair · gpt-3.5-turbo

    specific years and associated events or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Haku
    -0.91
     Hes
    -0.85
    nos
    -0.83
    hands
    -0.80
    ssh
    -0.79
    hod
    -0.79
    Wik
    -0.78
     Goth
    -0.77
    Fle
    -0.77
    osaurs
    -0.76
    POSITIVE LOGITS
    ati
    0.94
    87
    0.82
    91
    0.82
    885
    0.81
     92
    0.80
     91
    0.80
    886
    0.79
     Marion
    0.79
    85
    0.78
    92
    0.78
    Act Density 0.559%

    No Known Activations