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

    Neuronpedia

    INDEX
    Explanations

    dates formatted as day+month or month+day

    oai_token-act-pair · gpt-3.5-turbo

    dates associated with events or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -1.01
    aditional
    -0.93
     practition
    -0.89
    ailability
    -0.85
     confir
    -0.84
    Þ
    -0.82
     oun
    -0.82
    ò
    -0.81
     pione
    -0.81
    oreAnd
    -0.81
    POSITIVE LOGITS
    th
    0.89
    ,
    0.80
    thia
    0.73
    vid
    0.69
    inx
    0.68
    iac
    0.67
    ember
    0.66
    zu
    0.66
    uary
    0.64
    NECT
    0.63
    Act Density 0.033%

    No Known Activations