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

    Neuronpedia

    INDEX
    Explanations

    concepts related to crime and judicial proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Disaster
    -0.17
     MIS
    -0.16
     confiscated
    -0.16
     destructive
    -0.16
     Thief
    -0.16
     Cata
    -0.15
    anken
    -0.15
    uits
    -0.15
     destruct
    -0.15
     Offensive
    -0.14
    POSITIVE LOGITS
     murder
    0.43
     killing
    0.40
     murders
    0.38
     killings
    0.38
    mur
    0.38
     murdered
    0.36
     kill
    0.35
     kills
    0.34
     killed
    0.34
    kill
    0.33
    Act Density 0.487%

    No Known Activations