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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criticism or theoretical discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icz
    -0.15
    ellido
    -0.14
    uer
    -0.14
    pac
    -0.14
    iez
    -0.14
     $('[
    -0.13
    uka
    -0.13
     ----------------------------------------------------------------------------------------------------------------
    -0.13
    ugu
    -0.13
    ãĤĵãģ¨
    -0.13
    POSITIVE LOGITS
     [
    0.18
     etc
    0.17
    [s
    0.16
    owler
    0.14
    Ń
    0.14
    minster
    0.14
    .quote
    0.14
    ¯
    0.13
     dirig
    0.13
    inant
    0.13
    Act Density 0.018%

    No Known Activations