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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or entities such as names of people, places, or organizations

    oai_token-act-pair · gpt-3.5-turbo

    articles and determiners (such as "a" and "an") preceding nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilty
    -0.91
    oper
    -0.83
    anism
    -0.83
    INO
    -0.78
    abilities
    -0.75
    alties
    -0.75
    Own
    -0.74
    Hon
    -0.74
    Avoid
    -0.73
    oots
    -0.71
    POSITIVE LOGITS
     flurry
    0.91
     mysterious
    0.89
     bombshell
    0.88
     spate
    0.85
     slew
    0.85
     group
    0.83
     woman
    0.82
     handful
    0.82
     gunman
    0.81
     commenter
    0.81
    Act Density 0.187%

    No Known Activations