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

    Neuronpedia

    INDEX
    Explanations

    words that indicate promises or assurances of satisfaction or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ToEnd
    -0.15
    arc
    -0.14
    oster
    -0.14
    .Selenium
    -0.14
    iler
    -0.14
    ild
    -0.14
    ington
    -0.14
    uy
    -0.14
    vvm
    -0.14
    ï½į
    -0.13
    POSITIVE LOGITS
    ably
    0.22
    /prom
    0.17
    anteed
    0.17
    ing
    0.16
    ÅĽ
    0.15
    ainty
    0.15
    0.15
    tesy
    0.14
    ean
    0.14
    ORTH
    0.14
    Act Density 0.029%

    No Known Activations