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

    Neuronpedia

    INDEX
    Explanations

    references to specificity and contrasting statements related to experiences or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏĦει
    -0.15
    _languages
    -0.15
    vik
    -0.15
     imz
    -0.15
    eric
    -0.15
    abay
    -0.14
    ''"
    -0.14
     yana
    -0.14
    екÑģи
    -0.14
     ÐĴики
    -0.14
    POSITIVE LOGITS
    ModelProperty
    0.15
    983
    0.15
    tn
    0.15
     cab
    0.14
    hazi
    0.14
    achen
    0.14
    inium
    0.14
    ovat
    0.14
     Tit
    0.14
    наÑĩе
    0.14
    Act Density 0.104%

    No Known Activations