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

    Neuronpedia

    INDEX
    Explanations

    references to the act of killing or death

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

    killing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CSP
    -0.50
    bolista
    -0.50
     xPos
    -0.49
     CMB
    -0.48
     _("
    -0.48
     Mateo
    -0.47
     للاسماء
    -0.47
     JAS
    -0.46
     PRC
    -0.46
     BEM
    -0.46
    POSITIVE LOGITS
     kill
    0.95
     killed
    0.90
     kills
    0.86
    Kill
    0.82
     Kill
    0.81
     KILL
    0.79
     Kills
    0.73
    Kills
    0.72
    killed
    0.72
     killing
    0.71
    Act Density 0.024%

    No Known Activations