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

    Neuronpedia

    INDEX
    Explanations

    different forms of mathematical expressions involving parentheses and operators

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     lé
    -0.54
     logar
    -0.52
    Mire
    -0.49
     comfor
    -0.49
    NameInMap
    -0.48
     Eriksson
    -0.48
    änien
    -0.48
     teck
    -0.48
    abase
    -0.47
    лья
    -0.47
    POSITIVE LOGITS
     itſelf
    0.82
     ViewHolder
    0.79
     JpaRepository
    0.75
     myſelf
    0.74
     WebDriverWait
    0.73
     Monfieur
    0.73
    enumii
    0.72
    neſs
    0.71
    ęku
    0.71
     entanto
    0.70
    Act Density 0.045%

    No Known Activations