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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns 'I' or 'we'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "I" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     adhesive
    -0.71
     Rolls
    -0.66
     hurting
    -0.65
     sucks
    -0.64
     Bake
    -0.64
     Bottom
    -0.63
     endif
    -0.61
     Alright
    -0.61
     gods
    -0.61
     antioxid
    -0.60
    POSITIVE LOGITS
    'm
    1.04
    aido
    1.04
    xtap
    1.01
    've
    0.97
     interviewed
    0.97
     visited
    0.96
    lan
    0.94
    ggy
    0.93
     witnessed
    0.91
    BD
    0.90
    Act Density 0.234%

    No Known Activations