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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating requests or invitations for feedback or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     understanding
    -0.27
     Understanding
    -0.24
     understood
    -0.23
    Understanding
    -0.22
     rozum
    -0.22
     familiarity
    -0.21
     Awareness
    -0.19
     awareness
    -0.19
     Knowledge
    -0.18
     understand
    -0.18
    POSITIVE LOGITS
     kn
    0.27
     know
    0.21
     kon
    0.20
     k
    0.20
    _k
    0.18
     km
    0.18
    Âłk
    0.17
     Know
    0.16
    No
    0.16
    .k
    0.16
    Act Density 0.095%

    No Known Activations