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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "it" and other personal pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hap
    -0.81
     Seat
    -0.74
    advertisement
    -0.66
    detail
    -0.66
     Seah
    -0.65
     Ballard
    -0.60
    2020
    -0.58
     halftime
    -0.57
     Kaplan
    -0.57
    088
    -0.57
    POSITIVE LOGITS
     wont
    0.86
     cant
    0.78
    izons
    0.74
    itiz
    0.73
    tarians
    0.71
     learnt
    0.69
    'll
    0.69
    ´
    0.68
     wors
    0.67
     should
    0.66
    Act Density 0.384%

    No Known Activations