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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating being the first to know or receive something

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing being the first to experience or learn about something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĨĴ
    -0.73
    ancies
    -0.70
    ļéĨĴ
    -0.69
    Ī
    -0.64
    IJ
    -0.63
    EStream
    -0.62
     teasp
    -0.61
     chap
    -0.61
    ĺħ
    -0.61
    Ļ
    -0.60
    POSITIVE LOGITS
    ggles
    0.95
    liest
    0.84
     admit
    0.84
     realize
    0.83
     congratulate
    0.83
    edge
    0.82
     realise
    0.80
    hest
    0.80
    ledged
    0.80
     confront
    0.78
    Act Density 0.060%

    No Known Activations