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

    Neuronpedia

    INDEX
    Explanations

    expressions of permission or requests to allow actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     familiarity
    -0.22
     understanding
    -0.21
     Knowledge
    -0.20
     Understanding
    -0.19
     Awareness
    -0.19
     awareness
    -0.19
     rozum
    -0.18
    aware
    -0.18
     knowledge
    -0.18
     understood
    -0.17
    POSITIVE LOGITS
     kn
    0.25
     kon
    0.17
     k
    0.17
     km
    0.16
    itesse
    0.15
     now
    0.15
     Kn
    0.15
    Ñĥмов
    0.14
    _k
    0.14
     Bliss
    0.14
    Act Density 0.086%

    No Known Activations