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

    Neuronpedia

    INDEX
    Explanations

    numerical values and terms related to calculations or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dud
    -0.17
     flatt
    -0.17
    óst
    -0.15
    cke
    -0.15
     تاب
    -0.14
    ypi
    -0.14
    dims
    -0.13
    Defaults
    -0.13
    riba
    -0.13
     Doll
    -0.13
    POSITIVE LOGITS
     difference
    0.45
     Difference
    0.40
    difference
    0.40
    Difference
    0.39
     Subtract
    0.34
     differences
    0.33
     subtract
    0.32
    å·®
    0.32
     subtraction
    0.30
    _difference
    0.28
    Act Density 0.120%

    No Known Activations