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

    Neuronpedia

    INDEX
    Explanations

    references to explosives and their triggering mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AspNetCore
    -0.44
    opp
    -0.41
    Quack
    -0.38
     Erl
    -0.38
    lsp
    -0.38
     critica
    -0.38
     registry
    -0.38
    SystemColors
    -0.36
     Leh
    -0.36
    avadoc
    -0.36
    POSITIVE LOGITS
     bomb
    1.07
    RenderAtEndOf
    1.03
     explosives
    1.00
     bombs
    0.99
     Bomb
    0.96
    bomb
    0.94
    Bomb
    0.91
    bombs
    0.88
     Bombs
    0.86
     bombing
    0.83
    Act Density 0.184%

    No Known Activations