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

    Neuronpedia

    INDEX
    Explanations

    statements made by individuals or organizations

    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
    -0.88
    upiter
    -0.80
    elsius
    -0.74
    vag
    -0.72
    existent
    -0.69
    estern
    -0.66
    nostic
    -0.65
    pei
    -0.64
    cffff
    -0.63
     pract
    -0.63
    POSITIVE LOGITS
     statement
    1.01
    Statement
    0.92
     announcing
    0.84
     emailed
    0.74
    soType
    0.73
     thanking
    0.73
    atures
    0.73
     warr
    0.72
     redes
    0.71
    terday
    0.71
    Act Density 0.025%

    No Known Activations