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

    Neuronpedia

    INDEX
    Explanations

    complex thoughts related to introspection and reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -1.13
    addCriterion
    -0.99
    AddTagHelper
    -0.94
    TintMode
    -0.93
    writeFieldEnd
    -0.93
     صوتيه
    -0.91
    ConstraintMaker
    -0.85
     فريبيس
    -0.83
     betweenstory
    -0.82
    NameInMap
    -0.82
    POSITIVE LOGITS
     think
    2.09
    Think
    2.04
     Think
    2.03
     thinking
    1.86
    think
    1.82
     imagine
    1.72
     THINK
    1.66
     thought
    1.62
     Thinking
    1.58
    Thinking
    1.58
    Act Density 0.341%

    No Known Activations