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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥŃãĥ¼
    -0.15
    enan
    -0.14
     lem
    -0.14
    uels
    -0.14
    atz
    -0.14
    asi
    -0.14
    ราย
    -0.14
     chew
    -0.13
     ALT
    -0.13
    NTAX
    -0.13
    POSITIVE LOGITS
     constants
    0.32
     constant
    0.29
     parameters
    0.28
     Constant
    0.27
     coefficients
    0.26
     Constants
    0.26
     weights
    0.26
     scale
    0.25
    constants
    0.25
     coeff
    0.25
    Act Density 0.391%

    No Known Activations