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

    Neuronpedia

    INDEX
    Explanations

    negations or expressions of skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.60
     remaining
    -0.58
    IEDAD
    -0.57
     Wikimedijinoj
    -0.55
    ลาย
    -0.53
     laver
    -0.52
     multiprocessing
    -0.52
     basically
    -0.51
     AppCompatTheme
    -0.51
    remaining
    -0.51
    POSITIVE LOGITS
    rungsseite
    0.71
     Bukan
    0.69
    ształ
    0.67
    ISupport
    0.67
    我不是
    0.66
    tagHelperRunner
    0.65
     lắm
    0.61
     bukanlah
    0.61
     AssemblyTitle
    0.60
    Bukan
    0.59
    Act Density 0.192%

    No Known Activations