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

    Neuronpedia

    INDEX
    Explanations

    variables and their relationships in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oute
    -0.17
    dens
    -0.17
    ucha
    -0.17
    izen
    -0.15
    olar
    -0.15
    anova
    -0.15
     Kelley
    -0.15
    izard
    -0.14
    ather
    -0.14
    (using
    -0.14
    POSITIVE LOGITS
    ÙĪØŃ
    0.17
    ãĥ¼ãĥĵ
    0.16
    åĬ¨çĶŁæĪIJ
    0.15
     Watkins
    0.14
    GF
    0.14
    VERTISE
    0.14
     Mk
    0.13
     æ¾
    0.13
     se
    0.13
    _gc
    0.13
    Act Density 0.008%

    No Known Activations