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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and verbs in past or present tense

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and their associated actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hap
    -0.82
    advertisement
    -0.69
     Seat
    -0.69
     Seah
    -0.66
    icative
    -0.59
    odor
    -0.57
    last
    -0.56
     bip
    -0.56
     Pediatrics
    -0.56
     Ballard
    -0.56
    POSITIVE LOGITS
     wont
    0.83
     cant
    0.72
    izons
    0.71
     guiActiveUn
    0.68
    ©¶æ¥µ
    0.68
     mole
    0.67
    ´
    0.66
    Ĥİ
    0.65
    $,
    0.65
     learnt
    0.64
    Act Density 0.361%

    No Known Activations