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

    Neuronpedia

    INDEX
    Explanations

    elements of structured discussions, specifically panel discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kaynağından
    -0.45
     morire
    -0.35
    amaño
    -0.34
     OMITTED
    -0.33
     éprou
    -0.33
     aimez
    -0.33
     mourir
    -0.32
     meurt
    -0.32
    infec
    -0.31
    ancial
    -0.31
    POSITIVE LOGITS
     debate
    0.81
     discussion
    0.78
     débat
    0.70
     debates
    0.69
     Debate
    0.68
     discussions
    0.67
    Discussion
    0.67
     Discussion
    0.64
    debate
    0.63
     débats
    0.61
    Act Density 0.336%

    No Known Activations