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

    Neuronpedia

    INDEX
    Explanations

    references to death and killing

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

    Referring to killing or destruction

    np_acts-logits-general · gemini-2.0-flash

    killing and destruction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AspNetCore
    -0.64
    rtc
    -0.56
    "}"
    -0.55
    >{@
    -0.55
     Tür
    -0.54
     età
    -0.54
     Farah
    -0.53
     Marav
    -0.53
     belakang
    -0.52
    Carrot
    -0.52
    POSITIVE LOGITS
     kill
    1.06
     kills
    0.95
    estroying
    0.92
     Kill
    0.88
     killing
    0.85
    kill
    0.84
    KILL
    0.84
     KILL
    0.83
    killing
    0.81
     destroy
    0.80
    Act Density 0.137%

    No Known Activations