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

    Neuronpedia

    INDEX
    Explanations

    sa- prefixed words that could refer to food preparation activities or locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "sausage."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INGTON
    -0.79
     Dragonbound
    -0.70
     Jenner
    -0.67
    LIN
    -0.66
    enegger
    -0.65
    etheless
    -0.63
    姫
    -0.62
     accounting
    -0.62
    hips
    -0.61
     GOODMAN
    -0.61
    POSITIVE LOGITS
    pling
    1.31
    plings
    1.15
    ven
    1.15
    arin
    1.06
    ucer
    1.06
    pping
    1.05
    pp
    1.04
    xon
    1.04
    ppy
    1.03
    vern
    1.02
    Act Density 0.012%

    No Known Activations