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

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific concepts and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    977
    -0.16
     fit
    -0.15
     Vera
    -0.15
    houette
    -0.15
    kiye
    -0.15
    arpa
    -0.14
    thing
    -0.14
    askell
    -0.14
    §è¡Į
    -0.14
     orient
    -0.14
    POSITIVE LOGITS
    asar
    0.16
    GD
    0.16
    omen
    0.16
    èľľ
    0.16
    adan
    0.16
     Wid
    0.16
     lòng
    0.15
    idas
    0.15
    æ½ľ
    0.15
    acher
    0.14
    Act Density 0.029%

    No Known Activations