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

    Neuronpedia

    INDEX
    Explanations

    terms related to criminal activities and justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Crime
    -0.19
    crime
    -0.17
     Crime
    -0.16
     crime
    -0.16
    eded
    -0.15
    unes
    -0.15
    gas
    -0.15
    ãĥªãĥ¼ãĤº
    -0.15
     rais
    -0.14
    CRM
    -0.14
    POSITIVE LOGITS
    ity
    0.26
     justice
    0.24
    ized
    0.22
    izing
    0.21
    izes
    0.21
    ization
    0.21
    istics
    0.21
    ize
    0.19
     Minds
    0.19
    ised
    0.19
    Act Density 0.007%

    No Known Activations