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

    Neuronpedia

    INDEX
    Explanations

    instances of murder or attempted murder and related criminal actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ریف
    -0.59
    Embar
    -0.59
    doria
    -0.55
     Embar
    -0.54
    iscus
    -0.54
    yasi
    -0.53
     Belajar
    -0.47
     NIL
    -0.46
     estoppel
    -0.46
    LIBRA
    -0.46
    POSITIVE LOGITS
     murder
    2.03
     killing
    2.01
     murders
    1.85
     kill
    1.83
     killings
    1.78
     murdering
    1.77
    murder
    1.72
     murdered
    1.67
     Murder
    1.66
     kills
    1.66
    Act Density 0.824%

    No Known Activations