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

    Neuronpedia

    INDEX
    Explanations

    personal possessive pronouns

    oai_token-act-pair · gpt-3.5-turbo

    references to the audience or the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    forth
    -0.91
    nown
    -0.76
    iors
    -0.75
    minus
    -0.74
    Serv
    -0.73
    laus
    -0.72
    schild
    -0.71
     Hort
    -0.70
    acca
    -0.69
    icably
    -0.68
    POSITIVE LOGITS
     own
    0.78
     browser
    0.77
     firewall
    0.74
     fingertips
    0.73
     doorstep
    0.70
     respective
    0.70
     ears
    0.69
     discretion
    0.69
     subscription
    0.69
     device
    0.68
    Act Density 0.028%

    No Known Activations