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

    Neuronpedia

    INDEX
    Explanations

    terms related to bladed weapons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    貨
    -0.17
    rics
    -0.17
    /Auth
    -0.16
    .Debugger
    -0.15
     addCriterion
    -0.15
    .mutable
    -0.15
    abol
    -0.15
    enance
    -0.15
    warts
    -0.14
    ouz
    -0.14
    POSITIVE LOGITS
    blade
    0.28
     wield
    0.27
     blade
    0.26
    -tip
    0.22
     handle
    0.22
     blades
    0.22
     tip
    0.22
    fish
    0.21
    -shaped
    0.21
    -handle
    0.21
    Act Density 0.096%

    No Known Activations