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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "when."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "When."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suit
    -0.67
     brace
    -0.66
     deserved
    -0.64
     potentially
    -0.62
     compet
    -0.62
     worth
    -0.62
     plac
    -0.60
    ady
    -0.59
     capital
    -0.58
     cru
    -0.58
    POSITIVE LOGITS
     When
    2.75
     Whenever
    2.18
    When
    2.14
     WHEN
    1.84
     During
    1.82
    when
    1.78
     Sometimes
    1.75
     While
    1.66
     Upon
    1.64
     Once
    1.64
    Act Density 0.024%

    No Known Activations