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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "obviously" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ạ
    -0.66
     sou
    -0.63
    AndEndTag
    -0.60
    findall
    -0.60
     capita
    -0.58
     thập
    -0.56
    multer
    -0.55
    weilen
    -0.55
     Cent
    -0.53
     ulang
    -0.53
    POSITIVE LOGITS
     obviously
    2.62
    obviously
    2.49
     Obviously
    2.29
    Obviously
    2.25
     obviamente
    1.92
     obvious
    1.89
    obvious
    1.80
     obvio
    1.68
    Obvious
    1.63
    VIOUS
    1.49
    Act Density 0.058%

    No Known Activations