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

    Neuronpedia

    INDEX
    Explanations

    proper nouns with a focus on famous names or brands

    oai_token-act-pair · gpt-3.5-turbo

    specific suffixes or parts of words that suggest a particular linguistic or thematic association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flan
    -0.80
     Foot
    -0.75
     Mahjong
    -0.75
    éĸ
    -0.72
     prepaid
    -0.72
     absentee
    -0.68
    Draft
    -0.68
     embell
    -0.66
     Holiday
    -0.66
     hook
    -0.65
    POSITIVE LOGITS
    us
    1.66
    os
    1.50
    osa
    1.24
    osite
    1.14
    OS
    1.11
    uses
    1.09
    US
    1.06
    ues
    1.06
    onomy
    1.02
    osal
    0.99
    Act Density 0.088%

    No Known Activations