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

    Neuronpedia

    INDEX
    Explanations

    the word "other" when it appears in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to external or alternative entities and ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utenant
    -0.82
    opus
    -0.71
    ony
    -0.70
     ç¥ŀ
    -0.66
    wark
    -0.65
    udence
    -0.64
    zai
    -0.63
    enced
    -0.62
    ouf
    -0.61
    selage
    -0.61
    POSITIVE LOGITS
    worldly
    2.04
     kinds
    1.23
     aspects
    1.22
     countries
    1.18
     types
    1.13
     avenues
    1.12
     factors
    1.08
     forms
    1.06
     disciplines
    1.04
     parts
    1.03
    Act Density 0.104%

    No Known Activations