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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical values and specific formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     November
    -0.17
    arov
    -0.15
    lamaz
    -0.15
     seven
    -0.15
    _argv
    -0.15
     McInt
    -0.15
     six
    -0.14
     five
    -0.14
    .ColumnHeader
    -0.14
     XI
    -0.14
    POSITIVE LOGITS
    14
    0.44
    13
    0.40
    15
    0.36
    åįģåĽĽ
    0.30
    16
    0.29
     XIV
    0.27
     fourteen
    0.27
    åįģä¸ī
    0.26
     thirteen
    0.25
    17
    0.23
    Act Density 0.059%

    No Known Activations