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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating timing or conditional situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bezeichneter
    -0.84
     Fid
    -0.78
     Indah
    -0.70
     Shrewsbury
    -0.67
    Hush
    -0.65
    ArrowToggle
    -0.64
    افظة
    -0.63
    addChild
    -0.60
     bezit
    -0.60
    ます
    -0.60
    POSITIVE LOGITS
     when
    1.56
    when
    1.48
     WHEN
    1.46
     When
    1.39
    When
    1.36
    WHEN
    1.33
    cuando
    1.24
     när
    1.22
     cuando
    1.20
    Cuando
    1.16
    Act Density 0.129%

    No Known Activations