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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating readiness or preparedness for action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stay
    -0.17
    ÙģاÙĤ
    -0.17
    عاÙĨ
    -0.16
    бÑĥÑĤ
    -0.15
     stays
    -0.15
    äter
    -0.15
    styleType
    -0.15
    /Typography
    -0.15
    ité
    -0.14
    pra
    -0.14
    POSITIVE LOGITS
     tackle
    0.21
     rock
    0.21
     action
    0.20
     accept
    0.20
     begin
    0.19
     tackling
    0.19
     go
    0.18
     rum
    0.18
     tackled
    0.18
     Go
    0.17
    Act Density 0.052%

    No Known Activations