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

    Neuronpedia

    INDEX
    Explanations

    Roman numerals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sequels or titles in a series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Marsh
    -0.73
     Photographer
    -0.70
    apo
    -0.64
     =================
    -0.63
     Liver
    -0.63
    acci
    -0.63
    peria
    -0.63
     imag
    -0.63
    LAB
    -0.62
    iPhone
    -0.61
    POSITIVE LOGITS
     crate
    0.67
    adium
    0.65
     Mercenary
    0.64
    TPS
    0.64
     precedence
    0.64
    icular
    0.63
    mentioned
    0.62
    kefeller
    0.62
     crates
    0.61
    ably
    0.61
    Act Density 0.000%

    No Known Activations