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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and notations related to functions and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ERO
    -0.16
    bras
    -0.16
    legg
    -0.15
    erif
    -0.14
    ÏĦια
    -0.14
     dÄĽt
    -0.14
    ÑĦоÑĢми
    -0.14
    arkin
    -0.14
    ocha
    -0.14
    arpa
    -0.14
    POSITIVE LOGITS
     ±
    0.52
    ±
    0.49
     +/-
    0.39
    pm
    0.36
     +-
    0.31
    ±n
    0.28
    +-
    0.28
     pm
    0.27
    PM
    0.26
     PM
    0.25
    Act Density 0.033%

    No Known Activations