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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the cessation of previous states or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾
    -0.81
     Enhancement
    -0.80
    Stars
    -0.70
    osite
    -0.67
    imov
    -0.67
    æĺ
    -0.67
     Colour
    -0.65
    achev
    -0.64
    é¾įåĸļ士
    -0.63
     Ding
    -0.63
    POSITIVE LOGITS
    adays
    0.86
     bothering
    0.79
     wedd
    0.79
     tolerated
    0.79
     tolerate
    0.76
     bothered
    0.76
     bother
    0.75
     extant
    0.75
     residing
    0.75
     exists
    0.75
    Act Density 0.013%

    No Known Activations