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

    Neuronpedia

    INDEX
    Explanations

    dates written in "day, month year" format

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number 23 in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mble
    -0.82
    ktop
    -0.70
    awaru
    -0.70
     Beir
    -0.69
    onic
    -0.66
     beaten
    -0.65
     assum
    -0.65
    chwitz
    -0.64
    uyomi
    -0.64
    atown
    -0.63
    POSITIVE LOGITS
    rd
    1.60
    RD
    0.93
    00
    0.90
    RF
    0.90
    23
    0.80
    ATH
    0.77
    MU
    0.77
    PATH
    0.75
    VEL
    0.75
    DS
    0.73
    Act Density 0.023%

    No Known Activations