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

    Neuronpedia

    INDEX
    Explanations

    references to criminal acts and legal proceedings

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

    homicidal death

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.48
     tadi
    -0.38
     متعلقه
    -0.33
     really
    -0.33
    .*")]
    -0.33
    ConstraintMaker
    -0.32
     vč
    -0.32
     demain
    -0.30
     mỏng
    -0.30
     gitu
    -0.30
    POSITIVE LOGITS
     disambiguazione
    0.70
    当時
    0.61
     damals
    0.58
    当时的
    0.58
    当时
    0.58
     onCancelled
    0.58
    当時は
    0.57
    ImageContext
    0.55
    当時の
    0.55
    那时候
    0.54
    Act Density 0.028%

    No Known Activations