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

    Neuronpedia

    INDEX
    Explanations

    dates mentioned in a specific context or structure

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "On" followed by a date

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MODE
    -0.88
    ãĤ¼ãĤ¦ãĤ¹
    -0.77
    949
    -0.69
    YP
    -0.66
    QB
    -0.66
    2500
    -0.66
    SourceFile
    -0.66
    fml
    -0.64
    $$
    -0.63
    200000
    -0.63
    POSITIVE LOGITS
    coming
    1.25
    slaught
    1.25
     behalf
    1.09
    eness
    0.98
    assis
    0.94
    yx
    0.92
    eday
    0.91
    etime
    0.90
    look
    0.87
    sight
    0.86
    Act Density 0.111%

    No Known Activations