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

    Neuronpedia

    INDEX
    Explanations

    references to intelligence and smartness in characters or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    smart enough

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     events
    -0.41
     its
    -0.35
    events
    -0.34
     other
    -0.34
     the
    -0.33
     latter
    -0.33
     services
    -0.32
     sessions
    -0.31
     encounter
    -0.31
     each
    -0.31
    POSITIVE LOGITS
     smartest
    1.45
     smarter
    1.39
     smart
    1.38
    smart
    1.34
    Smart
    1.25
     Smart
    1.23
     Smarter
    1.22
    Smar
    1.21
    SMART
    1.16
     SMART
    1.15
    Act Density 0.008%

    No Known Activations