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

    Neuronpedia

    INDEX
    Explanations

    words related to difficult situations and health-related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olini
    -0.17
    anou
    -0.16
    Fallback
    -0.15
    ηÏĤ
    -0.15
    ponsive
    -0.15
    tings
    -0.15
    ERGE
    -0.14
    isko
    -0.14
    lix
    -0.14
     ç
    -0.14
    POSITIVE LOGITS
    fold
    0.18
     Folding
    0.15
     Snyder
    0.14
    apg
    0.14
     yo
    0.14
    agine
    0.14
     folding
    0.13
     Peng
    0.13
    untu
    0.13
     Fold
    0.13
    Act Density 0.002%

    No Known Activations