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

    Neuronpedia

    INDEX
    Explanations

    sentences describing events or situations that are happening currently

    oai_token-act-pair · gpt-3.5-turbo

    statements or assertions about a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    luaj
    -0.76
    elve
    -0.76
    opez
    -0.73
    styles
    -0.71
    bid
    -0.68
    asers
    -0.68
    dies
    -0.67
    chev
    -0.67
    esm
    -0.66
    ãĤ©
    -0.66
    POSITIVE LOGITS
     happening
    0.95
     definitely
    0.89
     supposed
    0.85
     NOT
    0.85
     gonna
    0.80
    nt
    0.80
     unacceptable
    0.78
     truly
    0.78
    rael
    0.78
     not
    0.77
    Act Density 0.123%

    No Known Activations