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

    Neuronpedia

    INDEX
    Explanations

    terms related to height comparisons and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÉR
    -0.46
     Gra
    -0.46
     Ul
    -0.45
    opan
    -0.43
    UGAL
    -0.42
    Mode
    -0.42
    judice
    -0.41
    addCriterion
    -0.40
    Референце
    -0.40
    ấu
    -0.40
    POSITIVE LOGITS
     size
    1.44
     length
    1.27
     height
    1.14
    size
    1.12
     lenght
    1.07
     width
    1.06
     sizes
    1.04
     SIZE
    1.01
    length
    0.95
     thickness
    0.95
    Act Density 0.485%

    No Known Activations