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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "when."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bezeichneter
    -0.89
    ArrowToggle
    -0.82
     Fid
    -0.80
    افظة
    -0.73
    曖昧さ回避
    -0.65
    Hush
    -0.64
    čko
    -0.63
    Cubit
    -0.62
     частности
    -0.62
     Livermore
    -0.61
    POSITIVE LOGITS
     when
    1.87
    when
    1.76
     WHEN
    1.70
    WHEN
    1.57
    When
    1.57
     When
    1.55
     cuando
    1.46
    cuando
    1.43
     när
    1.40
     quando
    1.36
    Act Density 0.135%

    No Known Activations