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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of learning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nut
    -0.18
    pa
    -0.17
    ford
    -0.16
    ged
    -0.16
    gaard
    -0.15
    ipi
    -0.15
    ga
    -0.15
    guards
    -0.15
    CreateInfo
    -0.15
    LP
    -0.15
    POSITIVE LOGITS
    /Instruction
    0.20
    _curve
    0.19
     curve
    0.19
     Curve
    0.18
    Curve
    0.17
    andro
    0.16
    -disabled
    0.16
     disabilities
    0.16
     Disabilities
    0.15
    ventory
    0.15
    Act Density 0.042%

    No Known Activations