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

    Neuronpedia

    INDEX
    Explanations

    references to societal issues and constraints involving race and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     roll
    -0.16
     Rolls
    -0.15
     Roll
    -0.14
     rolls
    -0.14
    -roll
    -0.14
    à¤Ĥपर
    -0.14
    ulk
    -0.14
    olu
    -0.13
    edy
    -0.13
     spying
    -0.13
    POSITIVE LOGITS
    omik
    0.15
    apia
    0.14
    aight
    0.14
    andon
    0.14
    ayne
    0.14
    iquer
    0.14
    OMEM
    0.13
    Ghost
    0.13
    .Clock
    0.13
    .measure
    0.13
    Act Density 1.438%

    No Known Activations