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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negation or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HW
    -0.17
    anova
    -0.16
    938
    -0.16
    ijo
    -0.16
    iston
    -0.15
    jon
    -0.15
    onomies
    -0.15
    sg
    -0.15
    iom
    -0.15
    uhe
    -0.15
    POSITIVE LOGITS
    æĪ¶
    0.15
     tas
    0.15
    zar
    0.15
    odiac
    0.15
    .Stack
    0.15
    ìĿ´íĬ¸
    0.15
    enos
    0.14
    ffset
    0.14
    aklı
    0.14
     vũ
    0.14
    Act Density 0.000%

    No Known Activations