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

    Neuronpedia

    INDEX
    Explanations

    words related to negative connotations or criticisms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "ill" indicating negative states or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ourke
    -0.72
    EStreamFrame
    -0.68
    ©¶æ¥µ
    -0.67
    EStream
    -0.66
    âĹ¼
    -0.63
    SPONSORED
    -0.61
    ļéĨĴ
    -0.59
    irrel
    -0.58
    SEA
    -0.58
    ICAN
    -0.58
    POSITIVE LOGITS
    uminati
    1.54
    ogical
    1.38
    umin
    1.33
    iberal
    1.30
    iquid
    1.24
    inois
    1.23
    usive
    1.22
    awar
    1.15
    usional
    0.97
    ugi
    0.89
    Act Density 0.017%

    No Known Activations