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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contemplation or deep thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rite
    -0.15
    pig
    -0.14
    解
    -0.14
    covering
    -0.14
    endoza
    -0.14
    rych
    -0.14
    715
    -0.13
     senses
    -0.13
     sect
    -0.13
    .Pointer
    -0.13
    POSITIVE LOGITS
     thought
    0.59
     thoughts
    0.58
     thinking
    0.56
    thought
    0.54
    thinking
    0.53
    think
    0.52
     THINK
    0.50
     think
    0.49
     Thought
    0.47
     Thinking
    0.47
    Act Density 0.352%

    No Known Activations