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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, primarily names and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GOODMAN
    -0.78
     conserv
    -0.69
    accompan
    -0.67
    PDATE
    -0.67
    âĢ¦âĢ¦âĢ¦âĢ¦
    -0.66
     DIRECT
    -0.65
    VERS
    -0.65
    QUEST
    -0.64
    NRS
    -0.63
    ³³³³³³³³³³³³³³³³
    -0.62
    POSITIVE LOGITS
    a
    1.20
    al
    1.18
    o
    1.15
    e
    1.13
    i
    1.03
    y
    1.02
    ei
    1.02
    ic
    0.98
    ar
    0.97
    u
    0.96
    Act Density 0.248%

    No Known Activations