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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by verbs in the context of actions or consequences

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific subject or object throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     LOT
    -0.68
    isky
    -0.65
    noticed
    -0.64
    EStreamFrame
    -0.63
     Fine
    -0.63
     Cycling
    -0.63
    Fine
    -0.62
    Interested
    -0.61
     Vu
    -0.59
    UGH
    -0.58
    POSITIVE LOGITS
     replaces
    1.12
     regulates
    1.07
     produces
    1.04
     entails
    1.03
     displ
    1.00
     generates
    0.98
     creates
    0.96
     serves
    0.96
     represents
    0.96
     consumes
    0.95
    Act Density 0.112%

    No Known Activations