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

    Neuronpedia

    INDEX
    Explanations

    the syllable "gin"

    oai_token-act-pair · gpt-4-turbo

    instances of the word "gin."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "gin."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     elapsed
    -0.74
     Immunity
    -0.66
     unintended
    -0.66
     odds
    -0.65
    gypt
    -0.65
     unforeseen
    -0.65
     accumulated
    -0.64
     punishment
    -0.64
     HHS
    -0.63
     HIP
    -0.62
    POSITIVE LOGITS
    gin
    1.37
    uine
    1.18
    atin
    1.05
    forth
    1.04
    uin
    1.02
    fo
    1.00
    osure
    0.97
    uit
    0.96
    ium
    0.92
     Rouge
    0.92
    Act Density 0.011%

    No Known Activations