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

    Neuronpedia

    INDEX
    Explanations

    references to scholarly citations or sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÄĽÅ¾
    -0.14
    ียà¸ĩ
    -0.14
    ungi
    -0.13
    ITY
    -0.13
    ãĥ©ãĤ¯
    -0.13
    hei
    -0.13
     Twist
    -0.13
    lub
    -0.13
    riteln
    -0.13
     striking
    -0.13
    POSITIVE LOGITS
    cheng
    0.15
    imoto
    0.14
     trough
    0.14
     watermark
    0.14
    imits
    0.14
    sole
    0.14
    帯
    0.13
    venir
    0.13
    _definitions
    0.13
     work
    0.13
    Act Density 0.002%

    No Known Activations