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

    Neuronpedia

    INDEX
    Explanations

    declarations or official remarks made in text

    oai_token-act-pair · gpt-3.5-turbo

    the word "statement."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.78
    elsius
    -0.77
    cffff
    -0.73
    skill
    -0.71
    animate
    -0.68
    upiter
    -0.68
    theless
    -0.66
     incumb
    -0.65
    vag
    -0.65
    otin
    -0.64
    POSITIVE LOGITS
     statement
    1.05
     emailed
    0.98
     announcing
    0.91
     issued
    0.88
    Statement
    0.86
     released
    0.81
     apologizing
    0.76
     acknowledging
    0.73
    atures
    0.73
     thanking
    0.73
    Act Density 0.032%

    No Known Activations