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

    Neuronpedia

    INDEX
    Explanations

    phrases that include the word "Conf" or "Confusion"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "Conf" indicating terms related to confidence or confessions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    senal
    -0.94
    BALL
    -0.81
    minecraft
    -0.74
    matically
    -0.71
    NING
    -0.70
    GY
    -0.69
    LOCK
    -0.69
    matical
    -0.68
    hyde
    -0.67
    ForgeModLoader
    -0.66
    POSITIVE LOGITS
    licts
    1.41
    licted
    1.33
    luence
    1.32
    idential
    1.29
    irmed
    1.25
    lict
    1.25
    irmation
    1.23
    irms
    1.15
    irming
    1.15
    erences
    1.13
    Act Density 0.016%

    No Known Activations