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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns referring to oneself

    oai_token-act-pair · gpt-3.5-turbo

    personal references or subjective expressions of experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tests
    -0.65
     envelope
    -0.65
     unfinished
    -0.64
    umption
    -0.63
     functionality
    -0.63
     gratification
    -0.62
     sunset
    -0.62
     scales
    -0.62
     storage
    -0.62
     pollut
    -0.62
    POSITIVE LOGITS
     whom
    1.27
    who
    1.19
    untled
    1.00
    friends
    1.00
     individuals
    0.99
    selves
    0.99
    those
    0.96
     representatives
    0.95
     acquaintances
    0.95
     yourselves
    0.95
    Act Density 0.487%

    No Known Activations