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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms related to firearms or violent actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.59
     Vaugh
    -0.54
     challeng
    -0.52
     disadvant
    -0.48
     Azerb
    -0.48
     blat
    -0.46
     advoc
    -0.46
     [*
    -0.46
     helicop
    -0.46
     cryst
    -0.44
    POSITIVE LOGITS
    \":
    0.43
    cigarettes
    0.40
     Belfast
    0.40
    ':
    0.39
    ¶
    0.39
     Corbyn
    0.39
    ratom
    0.38
    cipled
    0.38
     Hillary
    0.37
     âĢº
    0.36
    Act Density 2.285%

    No Known Activations