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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships and dependencies among subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _ARCHIVE
    -0.16
    IFS
    -0.16
    rary
    -0.15
    .ec
    -0.15
    ìļ°ë¦¬
    -0.15
    rial
    -0.14
    .rar
    -0.14
    letics
    -0.14
    ocket
    -0.14
    aja
    -0.14
    POSITIVE LOGITS
    ersen
    0.19
    éĺª
    0.15
    erb
    0.15
    reira
    0.14
    داÙħ
    0.14
    εÏĢ
    0.14
    vik
    0.13
     unpack
    0.13
     men
    0.13
    ungs
    0.13
    Act Density 0.008%

    No Known Activations