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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of individuals that may be of importance or interest

    oai_token-act-pair · gpt-3.5-turbo

    the word "who" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anything
    -0.73
     VIDEOS
    -0.69
     Anyway
    -0.66
    BACK
    -0.66
    ³³³³
    -0.65
     Bound
    -0.64
    ãĤª
    -0.64
     Beet
    -0.62
     Watching
    -0.61
     Federation
    -0.60
    POSITIVE LOGITS
     accompanies
    1.04
    oping
    1.02
     frequ
    1.01
    oped
    0.96
     resided
    0.95
     preceded
    0.94
     specializes
    0.93
    soever
    0.92
     attends
    0.90
     accompanied
    0.90
    Act Density 0.152%

    No Known Activations