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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "it" and related phrases suggesting subjectivity or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pai
    -0.70
    DNA
    -0.68
    PF
    -0.67
    iken
    -0.67
    JJ
    -0.64
    éĹĺ
    -0.63
    xia
    -0.62
    Target
    -0.62
    YP
    -0.62
    ajor
    -0.61
    POSITIVE LOGITS
     therein
    0.84
     importantly
    0.80
     accordingly
    0.76
     thereof
    0.74
     alike
    0.68
     cru
    0.67
     proceeded
    0.67
     conclud
    0.67
     sums
    0.66
     consequently
    0.65
    Act Density 0.341%

    No Known Activations