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

    Neuronpedia

    INDEX
    Explanations

    phrases related to in-depth analysis or exploration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    адÑĥ
    -0.15
     count
    -0.15
    vais
    -0.15
     binder
    -0.15
     consec
    -0.15
    chap
    -0.14
    atonin
    -0.14
    299
    -0.14
    quez
    -0.13
    762
    -0.13
    POSITIVE LOGITS
    idis
    0.16
    KO
    0.15
     паÑĢа
    0.14
    andre
    0.14
    peq
    0.14
     Leading
    0.14
    OTO
    0.13
    _UNUSED
    0.13
    ress
    0.13
    riter
    0.13
    Act Density 0.001%

    No Known Activations