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

    Neuronpedia

    INDEX
    Explanations

    words associated with knowledge, awareness, and significant concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enco
    -0.17
    erb
    -0.15
     Bitte
    -0.15
    åĪ¥
    -0.15
    bat
    -0.14
    alion
    -0.14
    isine
    -0.14
    QUAL
    -0.14
    μά
    -0.14
    roys
    -0.14
    POSITIVE LOGITS
    ante
    0.15
    usan
    0.15
     sausage
    0.15
    irit
    0.14
    America
    0.14
    å¨ľ
    0.14
    Bow
    0.14
    eto
    0.14
    -http
    0.14
    AGE
    0.13
    Act Density 0.015%

    No Known Activations