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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns or verbs indicating action or decision-making

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and expressions of assertion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Exit
    -0.75
    rocket
    -0.71
    culosis
    -0.70
    grass
    -0.69
    venge
    -0.68
    tops
    -0.65
    pause
    -0.65
    renheit
    -0.63
    classic
    -0.63
    shock
    -0.62
    POSITIVE LOGITS
     stated
    0.68
     noted
    0.65
     overest
    0.65
     hath
    0.64
     seems
    0.64
     aforementioned
    0.63
     perenn
    0.63
    ather
    0.63
     conceded
    0.63
     concedes
    0.62
    Act Density 0.404%

    No Known Activations