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

    Neuronpedia

    INDEX
    Explanations

    the pronoun "I" followed by a verb indicating a state or action

    oai_token-act-pair · gpt-3.5-turbo

    personal statements about identity and self-perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orthy
    -0.78
    sers
    -0.75
    enges
    -0.73
    ancial
    -0.73
    urrection
    -0.72
    negie
    -0.70
    wark
    -0.68
    forcement
    -0.67
    icators
    -0.66
    asury
    -0.66
    POSITIVE LOGITS
     addicted
    1.19
     allergic
    1.16
     obsessed
    1.15
     married
    1.06
     autistic
    1.04
     bisexual
    1.02
     fascinated
    1.01
     passionate
    1.00
     thankful
    1.00
     happiest
    0.99
    Act Density 0.266%

    No Known Activations