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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating actions or behaviors that someone is supposed to do or that involve making decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating possession or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nai
    -0.73
    Introduced
    -0.70
    Rated
    -0.69
    advertisement
    -0.68
     redes
    -0.67
    iership
    -0.66
    displayText
    -0.65
     predec
    -0.64
     Flavoring
    -0.63
     conclud
    -0.63
    POSITIVE LOGITS
     him
    1.55
     them
    1.49
     us
    1.17
     THEM
    1.14
     HIM
    1.05
     me
    1.02
    him
    1.00
     someone
    0.99
    them
    0.94
     everyone
    0.92
    Act Density 0.308%

    No Known Activations