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

    Neuronpedia

    INDEX
    Explanations

    instances where a statement contradicts something in the text

    oai_token-act-pair · gpt-3.5-turbo

    the word "not" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.81
    rift
    -0.78
    ixel
    -0.78
    arten
    -0.70
    istle
    -0.68
    TIME
    -0.67
     Tycoon
    -0.66
    Times
    -0.66
    ngth
    -0.63
    velt
    -0.62
    POSITIVE LOGITS
     necessarily
    1.29
    icable
    1.05
    etheless
    1.04
    epad
    0.96
    eworthy
    0.94
    icably
    0.90
    withstanding
    0.89
     enough
    0.84
    cially
    0.78
     bothering
    0.75
    Act Density 0.045%

    No Known Activations