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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "In a statement" or "said in a statement"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "statement."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.85
    elsius
    -0.81
    skill
    -0.70
    cffff
    -0.67
    nostic
    -0.65
    upiter
    -0.64
    vag
    -0.64
    otin
    -0.63
    animate
    -0.63
     mathemat
    -0.62
    POSITIVE LOGITS
     statement
    1.08
     announcing
    1.03
     emailed
    1.01
     issued
    0.95
     released
    0.92
     thanking
    0.85
    terday
    0.84
    Statement
    0.82
     accompanying
    0.81
    :"
    0.80
    Act Density 0.042%

    No Known Activations