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

    Neuronpedia

    INDEX
    Explanations

    references to violent incidents and casualties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raid
    -0.16
    destruct
    -0.16
    çĹ
    -0.15
    ENCH
    -0.15
     destructive
    -0.15
    REAK
    -0.15
    quare
    -0.14
    usta
    -0.14
     Destruction
    -0.14
    .managed
    -0.14
    POSITIVE LOGITS
     killed
    0.35
     Killed
    0.26
     electro
    0.26
     gun
    0.24
     shot
    0.23
    -k
    0.22
     sense
    0.21
     critically
    0.21
     pronounced
    0.21
     ki
    0.21
    Act Density 0.111%

    No Known Activations