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

    Neuronpedia

    INDEX
    Explanations

    references to murder or killing events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Embar
    -0.59
     متحده
    -0.58
    améli
    -0.57
    WSER
    -0.57
    noons
    -0.56
    digans
    -0.55
     Leaks
    -0.54
     Participant
    -0.54
     برانيه
    -0.53
    elementType
    -0.52
    POSITIVE LOGITS
     murder
    0.99
     killing
    0.96
     murdering
    0.93
     murders
    0.91
    murder
    0.90
     kill
    0.87
     slaughter
    0.87
     homicide
    0.86
     killings
    0.85
     kills
    0.83
    Act Density 0.106%

    No Known Activations