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

    Neuronpedia

    INDEX
    Explanations

    references to question-and-answer formats or interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieri
    -0.16
    веÑī
    -0.15
    ifter
    -0.15
    tru
    -0.15
    ères
    -0.14
     Sik
    -0.14
    ÅĻiv
    -0.14
    keit
    -0.14
     ÑĤÑĢав
    -0.14
    jÅ¡ÃŃ
    -0.14
    POSITIVE LOGITS
    estion
    0.16
    åĦ
    0.15
    olare
    0.14
    uliar
    0.14
    chie
    0.14
    imity
    0.14
     answers
    0.13
     switch
    0.13
     ole
    0.13
    enger
    0.13
    Act Density 0.026%

    No Known Activations