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

    Neuronpedia

    INDEX
    Explanations

    phrases that specify instances of death or murder involving individuals

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

    death of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.47
     useRouter
    -0.46
    stdc
    -0.46
    LayoutStyle
    -0.46
    fjspx
    -0.45
    prepareStatement
    -0.45
    HideFlags
    -0.45
    ResumeLayout
    -0.45
    出版年
    -0.44
    pushFollow
    -0.44
    POSITIVE LOGITS
    杀死
    0.49
     killed
    0.48
     deceased
    0.45
     kehilangan
    0.45
     killing
    0.45
     Gefang
    0.45
     captured
    0.45
    injured
    0.44
     betweenstory
    0.44
     murdered
    0.42
    Act Density 0.030%

    No Known Activations