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

    Neuronpedia

    INDEX
    Explanations

    words related to negative connotations or criticism

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the term "ill" paired with various contexts suggesting negativity or inadequacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.80
    EStream
    -0.78
    ļéĨĴ
    -0.77
    £ı
    -0.75
    EStreamFrame
    -0.75
    uyomi
    -0.74
     compr
    -0.69
    kefeller
    -0.68
    theless
    -0.68
    ©¶æ¥µ
    -0.66
    POSITIVE LOGITS
    uminati
    1.44
    inois
    1.24
    ogical
    1.16
    iberal
    1.16
    umin
    1.15
    awar
    1.13
    icit
    1.07
    usive
    1.03
    nesses
    1.00
    igan
    0.99
    Act Density 0.016%

    No Known Activations