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

    Neuronpedia

    INDEX
    Explanations

    contractions with an apostrophe preceding 's'

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms or contractions indicating ownership or belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.79
     Cosponsors
    -0.72
    abor
    -0.72
    ventures
    -0.70
    nered
    -0.70
     Flavoring
    -0.70
    yne
    -0.67
    Brit
    -0.64
    atl
    -0.64
    hof
    -0.63
    POSITIVE LOGITS
     automatically
    1.04
     gonna
    1.01
     forfeit
    0.98
     guaranteed
    0.97
     gravy
    0.93
     indistinguishable
    0.93
     likely
    0.92
     worthless
    0.92
     okay
    0.91
     liable
    0.89
    Act Density 0.227%

    No Known Activations