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

    Neuronpedia

    INDEX
    Explanations

    language related to legal accusations and serious offenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÅĻet
    -0.15
    .Selenium
    -0.14
    yst
    -0.14
    à¹Ĥà¸ĭ
    -0.14
    559
    -0.13
     blackmail
    -0.13
    ilerden
    -0.13
     extortion
    -0.13
    iker
    -0.13
    anging
    -0.13
    POSITIVE LOGITS
     crime
    0.61
     crimes
    0.53
    crime
    0.47
     Crime
    0.44
     offense
    0.42
     offenses
    0.40
     acts
    0.40
     Crimes
    0.40
    Crime
    0.38
     offence
    0.38
    Act Density 0.305%

    No Known Activations