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

    Neuronpedia

    INDEX
    Explanations

    numeric patterns or sequences related to data values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WithFormat
    -0.81
    Hentet
    -0.69
     الحره
    -0.68
    SourceChecksum
    -0.66
    apimachinery
    -0.66
    NamedQueries
    -0.66
    :✨
    -0.65
    曖昧さ回避
    -0.64
    UnknownFieldSet
    -0.64
     springfox
    -0.64
    POSITIVE LOGITS
    5
    0.59
    0
    0.57
    2
    0.52
    7
    0.51
    8
    0.50
    3
    0.50
    9
    0.50
    6
    0.48
    expandindo
    0.47
    Fixed
    0.47
    Act Density 0.274%

    No Known Activations