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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming functions and variables in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hyp
    -0.16
    .generated
    -0.15
    obi
    -0.15
    hyp
    -0.14
    utoff
    -0.14
    ãĥ³ãĤ°ãĥ«
    -0.14
    nette
    -0.14
    haus
    -0.14
    056
    -0.14
    away
    -0.14
    POSITIVE LOGITS
    tsy
    0.16
    adle
    0.15
    olest
    0.15
    iola
    0.14
    /views
    0.14
    廳
    0.14
    OLF
    0.14
    igo
    0.14
    igm
    0.14
    olia
    0.14
    Act Density 0.193%

    No Known Activations