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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating that something is "no longer" in a particular state or condition

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating the cessation or termination of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾
    -0.80
     Enhancement
    -0.79
    æĺ
    -0.67
     Colour
    -0.65
    Stars
    -0.65
    achev
    -0.65
    imov
    -0.65
    osite
    -0.64
    é¾įåĸļ士
    -0.61
     Ding
    -0.61
    POSITIVE LOGITS
    adays
    0.85
     bothering
    0.77
     exists
    0.76
     obsolete
    0.76
     tolerated
    0.75
     wedd
    0.74
     bothered
    0.74
     bother
    0.74
     residing
    0.73
     extant
    0.73
    Act Density 0.053%

    No Known Activations