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

    Neuronpedia

    INDEX
    Explanations

    references to cognitive processes and reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vettore
    -0.71
     vettoriale
    -0.60
    meliharaan
    -0.60
    ampi
    -0.58
     őket
    -0.58
     popolari
    -0.57
    ponym
    -0.56
     riconoscimento
    -0.56
    териалы
    -0.54
    Награды
    -0.54
    POSITIVE LOGITS
     thinking
    3.47
     Thinking
    3.23
    Thinking
    3.06
    thinking
    3.00
     thinkers
    2.28
     THINK
    2.25
     thinker
    2.13
     thought
    2.06
     Thought
    2.06
     thoughts
    2.04
    Act Density 0.092%

    No Known Activations