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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to health and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Drum
    -0.16
    abet
    -0.15
    anga
    -0.15
    emoji
    -0.15
    ÑĢедиÑĤ
    -0.15
    aklı
    -0.14
    usk
    -0.14
    jury
    -0.14
    /rs
    -0.14
    _Framework
    -0.14
    POSITIVE LOGITS
    ean
    0.20
    illes
    0.17
    edo
    0.16
    abwe
    0.16
    arra
    0.15
     CSI
    0.15
    raction
    0.14
    ottes
    0.14
    alis
    0.14
     Lif
    0.14
    Act Density 0.024%

    No Known Activations