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

    Neuronpedia

    INDEX
    Explanations

    references to formal documentation and guidelines in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ITA
    -0.17
    ìĨ
    -0.16
    ylv
    -0.15
    èĻİ
    -0.14
     NavParams
    -0.14
    à¤Ĺल
    -0.14
    abet
    -0.14
    _WP
    -0.14
    unknown
    -0.13
     cụ
    -0.13
    POSITIVE LOGITS
    457
    0.16
    ãĥ¡ãĥ³ãĥĪ
    0.15
    umn
    0.15
    991
    0.15
    çŃĴ
    0.15
    ving
    0.15
    -NLS
    0.14
     Monk
    0.14
    987
    0.14
     general
    0.14
    Act Density 0.425%

    No Known Activations