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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "no" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    koa
    -0.16
    rollo
    -0.15
     Vader
    -0.14
    ko
    -0.14
    bee
    -0.14
    ru
    -0.14
    hev
    -0.14
    pga
    -0.14
     anybody
    -0.14
    soever
    -0.14
    POSITIVE LOGITS
    veau
    0.28
    sey
    0.27
    xious
    0.25
    thern
    0.23
    okie
    0.22
    odge
    0.22
    seg
    0.21
    things
    0.21
    itamin
    0.20
    oks
    0.20
    Act Density 0.039%

    No Known Activations