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

    Neuronpedia

    INDEX
    Explanations

    instances of formatting or structural indicators in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InputBorder
    -0.75
    MeasureSpec
    -0.68
    COUP
    -0.66
    ItemBackground
    -0.66
    CodedInputStream
    -0.66
    NUMX
    -0.64
    LookAnd
    -0.64
     ideas
    -0.63
    ensement
    -0.63
    љено
    -0.61
    POSITIVE LOGITS
    0.78
    Datuak
    0.73
    titian
    0.72
     adequacy
    0.59
    tvguidetime
    0.59
    Xiv
    0.56
    <bos>
    0.55
    fork
    0.55
    UMBIA
    0.54
    ̸
    0.53
    Act Density 0.050%

    No Known Activations