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

    Neuronpedia

    INDEX
    Explanations

    phrases that express negation or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elerde
    -0.15
    ategor
    -0.14
     nues
    -0.14
    atego
    -0.14
     sec
    -0.14
     Matthews
    -0.14
    rike
    -0.14
    gener
    -0.14
     nonatomic
    -0.14
    esco
    -0.14
    POSITIVE LOGITS
    ices
    0.20
    iced
    0.20
     everyone
    0.19
    CHED
    0.18
    icias
    0.17
     necessarily
    0.17
    icies
    0.17
     surprisingly
    0.16
    least
    0.16
    ieder
    0.16
    Act Density 0.030%

    No Known Activations