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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of 'not' or negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    es
    -0.18
    hart
    -0.18
    o
    -0.16
    yor
    -0.15
    eri
    -0.15
    dre
    -0.15
    itra
    -0.14
    MeasureSpec
    -0.14
    alf
    -0.14
    amo
    -0.14
    POSITIVE LOGITS
    esseract
    0.21
    ting
    0.19
    aurus
    0.19
    rell
    0.16
    rench
    0.15
    ledge
    0.15
    ceans
    0.15
    swana
    0.15
    unnel
    0.15
    tery
    0.15
    Act Density 0.068%

    No Known Activations