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

    Neuronpedia

    INDEX
    Explanations

    expressions of regret or negativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AttributeSet
    -0.70
    
    -0.65
    PointerException
    -0.62
    osoever
    -0.59
     cwt
    -0.58
    ramanian
    -0.58
    abetes
    -0.58
    AntiForgeryToken
    -0.58
    ător
    -0.57
    ⟬
    -0.57
    POSITIVE LOGITS
    Unfortunately
    1.00
     unfortunately
    1.00
    Sadly
    0.95
     Unfortunately
    0.93
    unfortunately
    0.92
     sadly
    0.87
     Leider
    0.86
     Sadly
    0.85
    Leider
    0.84
    värr
    0.83
    Act Density 0.126%

    No Known Activations