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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and variables used in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    linkplain
    -0.16
    aspers
    -0.15
    onus
    -0.15
    <[
    -0.14
    ung
    -0.14
     Ung
    -0.14
    cycle
    -0.14
    leur
    -0.14
    heits
    -0.14
    essler
    -0.14
    POSITIVE LOGITS
     +
    0.49
     plus
    0.38
     плÑİ
    0.28
    ()+
    0.25
    +
    0.25
     +↵
    0.22
     Plus
    0.21
     addition
    0.21
     together
    0.21
     +#
    0.20
    Act Density 0.138%

    No Known Activations