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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical definitions and relationships

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     S
    -0.51
    бы
    -0.48
    S
    -0.47
    div
    -0.47
    econ
    -0.47
    -
    -0.46
    :
    -0.46
     F
    -0.46
    ##
    -0.45
     project
    -0.45
    POSITIVE LOGITS
     estekak
    1.14
    SourceChecksum
    1.05
     الرياضيه
    0.95
     Majefty
    0.94
     Theſe
    0.92
     تضيفلها
    0.91
    LookAnd
    0.90
     препратки
    0.89
     transfieras
    0.87
    NUMX
    0.87
    Act Density 0.016%

    No Known Activations