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

    Neuronpedia

    INDEX
    Explanations

    variables and mathematical functions related to algebraic expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    <eos>
    -0.53
    ↵↵
    -0.49
    "
    -0.47
    ''
    -0.46
    si
    -0.46
    '
    -0.45
    ts
    -0.45
    </i>
    -0.44
     [
    -0.44
    ’
    -0.44
    POSITIVE LOGITS
    Personendaten
    1.02
    \{\\
    0.91
     للمعارف
    0.86
    ConstraintMaker
    0.83
    ///</
    0.77
     lenker
    0.77
     myſelf
    0.76
     Савезне
    0.75
     protoimpl
    0.75
    NUMX
    0.75
    Act Density 0.031%

    No Known Activations