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

    Neuronpedia

    INDEX
    Explanations

    numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uden
    -0.79
    matically
    -0.75
    faced
    -0.70
    inges
    -0.69
    falls
    -0.68
    gets
    -0.68
    arted
    -0.67
    tons
    -0.65
    lying
    -0.64
    lie
    -0.64
    POSITIVE LOGITS
    IRC
    0.84
    ¯¯¯¯
    0.83
    ASC
    0.82
    REM
    0.80
    clair
    0.79
    oice
    0.73
    EMENT
    0.73
    SPA
    0.72
    80
    0.71
     cents
    0.70
    Act Density 0.058%

    No Known Activations