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

    Neuronpedia

    INDEX
    Explanations

    words related to specific dates and events

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific repeating token or character pattern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orescence
    -0.84
    oresc
    -0.81
    itud
    -0.80
    glers
    -0.79
    abwe
    -0.73
    oaded
    -0.71
    ciating
    -0.68
    enos
    -0.67
    urat
    -0.67
    arsity
    -0.67
    POSITIVE LOGITS
    0.98
    Leaks
    0.85
    âĢ¢âĢ¢
    0.85
    Bloomberg
    0.81
    0.81
    NOR
    0.78
    Canada
    0.75
    everyone
    0.74
    SER
    0.73
    Ö¼
    0.73
    Act Density 0.022%

    No Known Activations