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

    Neuronpedia

    INDEX
    Explanations

    references to flatness or level surfaces in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holes
    -0.16
    emas
    -0.15
     Frid
    -0.15
    kla
    -0.14
    luv
    -0.14
    È
    -0.14
    romium
    -0.14
    iba
    -0.14
    _subplot
    -0.14
    باÙĨ
    -0.14
    POSITIVE LOGITS
    ulence
    0.20
    ulent
    0.17
    -flat
    0.17
    ernal
    0.17
    ¼
    0.16
    -ÑĤаки
    0.15
    ness
    0.15
    ened
    0.15
    flat
    0.15
    ishments
    0.15
    Act Density 0.034%

    No Known Activations