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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and modifiers that indicate contrast or exception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    In
    -0.53
     vyk
    -0.52
    ūras
    -0.51
    .
    -0.50
     postes
    -0.48
     soledad
    -0.48
    绎
    -0.48
    I
    -0.48
     I
    -0.48
     dikk
    -0.47
    POSITIVE LOGITS
    BufferException
    1.16
    ThemeOverlay
    0.81
    الحياه
    0.80
     lecz
    0.76
    EnableWeb
    0.74
    AddHtmlAttribute
    0.73
    iastes
    0.71
    /*
    0.70
     ConstraintSet
    0.70
    却又
    0.68
    Act Density 0.161%

    No Known Activations