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

    Neuronpedia

    INDEX
    Explanations

    phrases related to violent acts and their victims

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    idth
    -0.74
    Applic
    -0.68
    FML
    -0.68
    RET
    -0.65
     cancell
    -0.65
    osterone
    -0.61
    Balt
    -0.61
    ãĥ¼ãĥĨ
    -0.60
    WARN
    -0.60
    Īè
    -0.59
    POSITIVE LOGITS
     unarmed
    1.04
     innoc
    1.00
     innocent
    0.98
     indiscrim
    0.91
     senseless
    0.91
     bystanders
    0.87
     fleeing
    0.86
     peacefully
    0.86
     hostage
    0.83
     hostages
    0.81
    Act Density 0.175%

    No Known Activations