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

    Neuronpedia

    INDEX
    Explanations

    references to explosions and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hezza
    -0.43
     mig
    -0.41
    แ
    -0.40
     mo
    -0.39
     Grund
    -0.39
     churras
    -0.38
     och
    -0.38
     basic
    -0.37
    ISF
    -0.37
    ülen
    -0.37
    POSITIVE LOGITS
     explosions
    1.25
     deton
    1.21
     exploding
    1.15
     explosion
    1.13
     explosives
    1.12
     detonation
    1.11
     bomb
    1.10
     bombs
    1.09
     bombing
    1.07
    bomb
    1.05
    Act Density 0.332%

    No Known Activations