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

    Neuronpedia

    INDEX
    Explanations

    numbers indicating dates

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number 29

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allo
    -0.79
    omial
    -0.78
    ates
    -0.77
    ento
    -0.75
    atorial
    -0.74
    algia
    -0.73
    omatic
    -0.71
    rid
    -0.70
    ĸļ
    -0.70
    ovie
    -0.69
    POSITIVE LOGITS
    00
    1.01
    09
    0.90
    06
    0.87
    VEL
    0.85
    08
    0.85
    theless
    0.83
    ATH
    0.82
    05
    0.80
    07
    0.79
    29
    0.78
    Act Density 0.017%

    No Known Activations