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

    Neuronpedia

    INDEX
    Explanations

    proper nouns referring to specific entities like people, places, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of people and examples of their experiences or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heid
    -0.65
    enium
    -0.65
    ysics
    -0.62
    otiation
    -0.61
    astern
    -0.61
    blast
    -0.61
    uild
    -0.60
    ustomed
    -0.60
    ulk
    -0.60
    ]+
    -0.58
    POSITIVE LOGITS
     notable
    0.95
     include
    0.84
     noteworthy
    0.83
    orthy
    0.82
     involves
    0.78
     highlights
    0.78
     includes
    0.78
     included
    0.72
    %:
    0.71
     however
    0.69
    Act Density 0.381%

    No Known Activations