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

    Neuronpedia

    INDEX
    Explanations

    variations of the verb "do" in the context of effects or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rok
    -0.15
    kar
    -0.15
    ptron
    -0.14
    swire
    -0.14
    ĤŃ
    -0.14
    ku
    -0.14
    ritten
    -0.14
    iny
    -0.14
    Actions
    -0.13
    conduct
    -0.13
    POSITIVE LOGITS
     wonders
    0.38
     justice
    0.31
     wonder
    0.27
     Wonder
    0.25
     wondered
    0.22
     damage
    0.22
     duty
    0.22
     away
    0.21
     violence
    0.21
    justice
    0.21
    Act Density 0.054%

    No Known Activations