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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or equations, particularly involving brackets and mathematical notation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    greif
    -0.61
     Dunbar
    -0.54
    ConstraintMaker
    -0.53
    ueling
    -0.53
     \[
    -0.52
    ptian
    -0.51
    Packs
    -0.51
     Keyes
    -0.50
    packs
    -0.49
    Royce
    -0.47
    POSITIVE LOGITS
    +#+#
    0.91
    SequentialGroup
    0.71
     חיצוניים
    0.71
    jsxFileName
    0.69
    enumi
    0.68
    ]")]
    0.67
     Pato
    0.67
    argout
    0.65
     bezeichneter
    0.64
     Winf
    0.63
    Act Density 0.021%

    No Known Activations