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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to various forms of fraud and corruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rible
    -0.17
    ensor
    -0.15
    imos
    -0.15
    htt
    -0.15
     Hack
    -0.14
    less
    -0.14
    à¸Ĺà¸ĺ
    -0.14
    icals
    -0.13
    ofday
    -0.13
     Dise
    -0.13
    POSITIVE LOGITS
     ring
    0.31
     rings
    0.28
     attempt
    0.24
    sters
    0.24
     Ring
    0.23
     Rings
    0.23
     charges
    0.23
    Ring
    0.23
     charge
    0.22
    ulence
    0.22
    Act Density 0.109%

    No Known Activations