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

    Neuronpedia

    INDEX
    Explanations

    references to killing or death

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

    "kill"

    np_acts-logits-general · gemini-2.0-flash

    kill, killing, or 殺

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.80
     AssemblyCulture
    -0.68
    󠁣
    -0.63
    zyp
    -0.63
    出版年
    -0.61
     republics
    -0.60
    rungsseite
    -0.59
     Baillargeon
    -0.59
    Према
    -0.58
    elemField
    -0.58
    POSITIVE LOGITS
     kill
    0.81
    kills
    0.79
     kills
    0.79
     KILL
    0.78
     Kill
    0.76
     tué
    0.74
     Kills
    0.71
    kill
    0.68
     killing
    0.64
    Kill
    0.61
    Act Density 0.087%

    No Known Activations