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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating cessation or a lack of interest in something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ally
    -0.19
    dez
    -0.15
    erate
    -0.15
     Gü
    -0.14
    oku
    -0.14
     Organ
    -0.13
    гÑĥ
    -0.13
    .override
    -0.13
    errupt
    -0.13
    uted
    -0.13
    POSITIVE LOGITS
    aring
    0.16
     há»ĵng
    0.14
    -of
    0.14
    /by
    0.14
    Ĥæķ°
    0.14
    arro
    0.14
    огод
    0.14
    erva
    0.13
    zd
    0.13
     ÅĻÃŃj
    0.13
    Act Density 0.013%

    No Known Activations