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

    Neuronpedia

    INDEX
    Explanations

    dates written in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "On" used to indicate specific dates or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MODE
    -0.91
    QB
    -0.77
    BP
    -0.69
    ãĤ¼ãĤ¦ãĤ¹
    -0.67
    $$
    -0.65
    SourceFile
    -0.64
    BIP
    -0.63
    utenberg
    -0.63
    Cod
    -0.63
    949
    -0.62
    POSITIVE LOGITS
    slaught
    1.20
    coming
    1.19
     behalf
    1.08
    eness
    1.06
    eday
    0.94
    assis
    0.93
    etheless
    0.93
    etime
    0.91
    yx
    0.91
     occasion
    0.88
    Act Density 0.080%

    No Known Activations