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

    Neuronpedia

    INDEX
    Explanations

    negations in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ennen
    -0.17
    789
    -0.15
    ENN
    -0.15
    ยว
    -0.14
    agle
    -0.14
    610
    -0.14
    rist
    -0.14
    .fhir
    -0.14
    ÑĤÑĢон
    -0.14
    unist
    -0.14
    POSITIVE LOGITS
     yet
    0.17
     Stap
    0.17
    avou
    0.16
    olls
    0.16
     ComVisible
    0.15
    bv
    0.15
    addy
    0.15
    Mocks
    0.15
    åŃĿ
    0.14
    ashed
    0.14
    Act Density 0.047%

    No Known Activations