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

    Neuronpedia

    INDEX
    Explanations

    proper nouns like names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and measurements related to events or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     persuasion
    -0.81
     purs
    -0.73
     dra
    -0.68
     incent
    -0.68
     ability
    -0.67
     renegoti
    -0.66
     circuits
    -0.66
     smoot
    -0.64
    iga
    -0.64
     afterlife
    -0.62
    POSITIVE LOGITS
    Interested
    1.21
    Writing
    1.16
    According
    1.16
    Specifically
    1.11
    Speaking
    1.08
    Sources
    1.07
    RELATED
    1.06
    While
    1.05
    Known
    1.03
    The
    1.02
    Act Density 0.433%

    No Known Activations