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

    Neuronpedia

    INDEX
    Explanations

    criteria and factors related to evaluations and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Directions
    -0.14
    sizes
    -0.14
    647
    -0.14
    REFERRED
    -0.14
     Sizes
    -0.13
    -urlencoded
    -0.13
    γκ
    -0.13
    ');?>
    -0.13
     Modes
    -0.13
    644
    -0.13
    POSITIVE LOGITS
     factors
    0.64
     variables
    0.56
     criteria
    0.49
     Factors
    0.48
     factor
    0.46
     parameters
    0.45
    variables
    0.43
     Variables
    0.43
     attributes
    0.43
    Factors
    0.43
    Act Density 0.353%

    No Known Activations