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

    Neuronpedia

    INDEX
    Explanations

    numbers preceded by the word "the."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the number 14 in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oyd
    -0.78
    atem
    -0.76
    ãĤ¡
    -0.72
    omial
    -0.70
    abwe
    -0.70
    ensibly
    -0.70
    ĸļ
    -0.68
     stocking
    -0.68
     Barnett
    -0.66
     PW
    -0.66
    POSITIVE LOGITS
    teenth
    1.12
    84
    0.92
    83
    0.90
    78
    0.89
    63
    0.88
    159
    0.88
    66
    0.86
    82
    0.86
    882
    0.86
    92
    0.86
    Act Density 0.025%

    No Known Activations