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

    Neuronpedia

    INDEX
    Explanations

    patterns and structures related to regular expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    landers
    -0.15
    lemn
    -0.15
    holm
    -0.14
    adesh
    -0.14
     Gos
    -0.14
    stry
    -0.13
    ellig
    -0.13
    ulen
    -0.13
    lessly
    -0.13
    igest
    -0.13
    POSITIVE LOGITS
    sb
    0.16
    kker
    0.16
    UpDown
    0.14
    ìĥī
    0.14
     outing
    0.14
    boro
    0.14
    ãĤ¤ãĥ³ãĥĪ
    0.14
    åĿª
    0.13
    inou
    0.13
    vangst
    0.13
    Act Density 0.019%

    No Known Activations