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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "denounce" or its variations, indicating disapproval or condemnation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hea
    -0.16
    ÅŁk
    -0.16
    inner
    -0.14
    å·
    -0.14
    rossover
    -0.14
    alam
    -0.14
    quets
    -0.14
    agner
    -0.14
    bben
    -0.14
    lice
    -0.14
    POSITIVE LOGITS
    unc
    0.30
    ouncing
    0.28
    ounce
    0.28
    unciation
    0.26
    unci
    0.26
    ouncements
    0.24
    ounces
    0.23
    iers
    0.22
    ational
    0.22
    ounc
    0.22
    Act Density 0.005%

    No Known Activations