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

    Neuronpedia

    INDEX
    Explanations

    references to accountability in software or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alom
    -0.17
    åĸĦ
    -0.16
    _BU
    -0.15
    adge
    -0.15
    encv
    -0.14
    forman
    -0.14
    jist
    -0.14
    noun
    -0.14
    AppName
    -0.14
    cken
    -0.13
    POSITIVE LOGITS
    yme
    0.16
    frey
    0.15
     Frid
    0.15
    ekler
    0.15
    ynet
    0.14
    ülü
    0.14
     Hib
    0.14
    agger
    0.14
    .ov
    0.14
    ç©´
    0.14
    Act Density 0.000%

    No Known Activations