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

    Neuronpedia

    INDEX
    Explanations

    words ending in "-inn"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "inn."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     litter
    -0.67
     flies
    -0.62
     caution
    -0.61
     follow
    -0.61
     courses
    -0.60
    lled
    -0.60
    lling
    -0.59
     ration
    -0.59
     critically
    -0.58
     tracts
    -0.58
    POSITIVE LOGITS
    ipeg
    1.30
    inn
    1.25
    igans
    1.16
    ikuman
    1.15
    igan
    1.08
    ovation
    1.06
    umerable
    1.05
    uin
    0.97
    athan
    0.93
    ipedia
    0.93
    Act Density 0.005%

    No Known Activations