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

    Neuronpedia

    INDEX
    Explanations

    times expressed in hours and minutes

    oai_token-act-pair · gpt-3.5-turbo

    time-related numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouver
    -0.77
    schild
    -0.77
    enhagen
    -0.73
    ittens
    -0.69
    roups
    -0.69
    lines
    -0.67
    atto
    -0.66
    abwe
    -0.66
    ulkan
    -0.65
    ensed
    -0.63
    POSITIVE LOGITS
    GHz
    0.72
    fter
    0.72
    ©¶æ
    0.70
     GHz
    0.70
     Centauri
    0.69
    ij士
    0.67
    mares
    0.66
    thood
    0.66
     Nieto
    0.64
     Viper
    0.62
    Act Density 0.109%

    No Known Activations