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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating preparation or readiness to act

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.19
     handjob
    -0.16
    stay
    -0.16
    styleType
    -0.16
     remained
    -0.15
     Remain
    -0.14
    pra
    -0.14
    /Typography
    -0.14
    ité
    -0.14
    äter
    -0.14
    POSITIVE LOGITS
     tackle
    0.21
     rock
    0.21
     tackling
    0.21
     action
    0.20
     accept
    0.20
     rum
    0.20
     tackled
    0.19
     Rock
    0.18
     hit
    0.18
     go
    0.18
    Act Density 0.072%

    No Known Activations