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

    Neuronpedia

    INDEX
    Explanations

    words ending in '-y', either with a vowel before the 'y' or with 'qu' before the 'y'

    oai_token-act-pair · gpt-3.5-turbo

    diminutive or affectionate suffixes and related word forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Polo
    -0.77
    Maps
    -0.71
     Cob
    -0.68
     Marriage
    -0.65
     Siber
    -0.64
     NX
    -0.64
     Xia
    -0.64
    Building
    -0.63
    Weather
    -0.61
     Frie
    -0.61
    POSITIVE LOGITS
    eenth
    0.93
    etheless
    0.85
    anging
    0.77
     suck
    0.73
    terday
    0.73
     mortals
    0.73
    urnal
    0.73
    ither
    0.72
    dozen
    0.71
    actory
    0.71
    Act Density 0.183%

    No Known Activations