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

    Neuronpedia

    INDEX
    Explanations

    pronouns for people

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities being discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pad
    -0.72
    termin
    -0.71
    Loading
    -0.71
    adder
    -0.70
    âĨ
    -0.70
    roads
    -0.70
    atory
    -0.66
    issue
    -0.64
    reach
    -0.63
    rid
    -0.63
    POSITIVE LOGITS
    soever
    1.97
    awei
    0.85
    selves
    0.81
    izens
    0.78
    osponsors
    0.77
    irlf
    0.75
     oun
    0.73
    owship
    0.73
     coh
    0.73
    aji
    0.71
    Act Density 0.019%

    No Known Activations