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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or notation involving operators and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Moraes
    -0.59
     Fizz
    -0.57
    Datuak
    -0.54
     Firth
    -0.51
    -0.51
    Diweddarwch
    -0.51
    ंदीखरीदारी
    -0.50
     atmospheres
    -0.50
    atility
    -0.50
    Sucesor
    -0.50
    POSITIVE LOGITS
    mathbf
    1.71
    boldsymbol
    0.87
    <b>
    0.68
     Woodruff
    0.59
     Bous
    0.57
    <strong>
    0.57
    modelBuilder
    0.57
    GraphicsUnit
    0.56
    ConstraintMaker
    0.56
    //
    0.56
    Act Density 0.240%

    No Known Activations