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

    Neuronpedia

    INDEX
    Explanations

    phrases related to killing or lethal actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     solidar
    -0.63
     stoff
    -0.61
     indeb
    -0.57
     Bourgoin
    -0.54
     unie
    -0.53
     impon
    -0.53
    cepan
    -0.52
     fras
    -0.52
     emoc
    -0.52
     zó
    -0.50
    POSITIVE LOGITS
     kill
    1.17
     killing
    1.09
     Kill
    1.07
     killed
    1.04
    Kill
    1.04
     kills
    1.02
    kill
    1.00
     Killing
    0.99
     KILL
    0.99
    killing
    0.94
    Act Density 0.130%

    No Known Activations