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

    Neuronpedia

    INDEX
    Explanations

    numerical data or code-related elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hud
    -0.16
    uddle
    -0.15
    夫
    -0.14
    .opend
    -0.14
    lub
    -0.14
    lun
    -0.14
    lum
    -0.14
     conce
    -0.14
    [loc
    -0.13
    redd
    -0.13
    POSITIVE LOGITS
    νε
    0.15
    iktig
    0.15
    orre
    0.15
    ideon
    0.14
    eneric
    0.14
    unes
    0.14
     Toll
    0.14
    ician
    0.14
    akk
    0.14
     Mineral
    0.13
    Act Density 0.046%

    No Known Activations