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

    Neuronpedia

    INDEX
    Explanations

    negations or words related to 'not.'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å±ĭ
    -0.18
    isle
    -0.17
    jee
    -0.17
    usterity
    -0.16
    .MixedReality
    -0.16
    locate
    -0.16
     {{--<
    -0.15
    ercial
    -0.15
    CanBe
    -0.15
    quam
    -0.15
    POSITIVE LOGITS
    ional
    0.27
    tingham
    0.26
    epad
    0.23
    icias
    0.23
    urnal
    0.22
     surprisingly
    0.20
    ational
    0.20
    ori
    0.20
    ices
    0.20
    ches
    0.19
    Act Density 0.043%

    No Known Activations