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

    Neuronpedia

    INDEX
    Explanations

    references to criminal charges and legal accusations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    charged with crimes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pushFollow
    -0.42
    ьажоргаш
    -0.42
     ویکی‌پدی
    -0.42
     Roskov
    -0.39
     Ideally
    -0.39
    OGND
    -0.38
     sterke
    -0.36
     desliz
    -0.36
     ideally
    -0.36
    verwijspagina
    -0.35
    POSITIVE LOGITS
     responsible
    0.57
     culprit
    0.52
    KommentareTeilen
    0.51
     perpetrator
    0.51
     offenses
    0.51
     offender
    0.50
     offenders
    0.50
    responsible
    0.49
     responsibility
    0.48
     responsável
    0.47
    Act Density 0.068%

    No Known Activations