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

    Neuronpedia

    INDEX
    Explanations

    mathematical variables and equations involving their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aad
    -0.15
     Borg
    -0.15
    ennen
    -0.15
    .unknown
    -0.14
    istrovstvÃŃ
    -0.14
    ût
    -0.14
    úa
    -0.14
    sted
    -0.14
    morgan
    -0.14
     Kendall
    -0.13
    POSITIVE LOGITS
    are
    0.35
    psilon
    0.33
    phant
    0.30
     epsilon
    0.27
    epsilon
    0.25
    .epsilon
    0.25
    space
    0.24
    eps
    0.23
    _epsilon
    0.23
    skip
    0.22
    Act Density 0.020%

    No Known Activations