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

    Neuronpedia

    INDEX
    Explanations

    proper nouns of people or entities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people, places, or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     clipboard
    -0.64
    CLASSIFIED
    -0.62
     antip
    -0.61
    uminati
    -0.61
     unequiv
    -0.59
     Occupations
    -0.58
     coerc
    -0.57
     congr
    -0.56
     curfew
    -0.56
    lihood
    -0.56
    POSITIVE LOGITS
    elia
    0.72
    gram
    0.69
    eson
    0.67
    ok
    0.67
    zon
    0.66
    oka
    0.66
    eware
    0.65
    mong
    0.65
    Pak
    0.65
    ek
    0.63
    Act Density 0.361%

    No Known Activations