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

    Neuronpedia

    INDEX
    Explanations

    words that denote a high level of quality or uniqueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erman
    -0.20
    chu
    -0.16
    soever
    -0.15
    .Euler
    -0.15
    aÅĻ
    -0.15
    emes
    -0.15
    uhn
    -0.15
    resco
    -0.14
    isset
    -0.14
    Ùħا
    -0.14
    POSITIVE LOGITS
    ordinary
    0.19
    -looking
    0.18
    -large
    0.17
    ively
    0.17
    ably
    0.16
     circumstances
    0.16
    ities
    0.16
    人çī©
    0.15
    uity
    0.15
    istically
    0.14
    Act Density 0.042%

    No Known Activations