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

    Neuronpedia

    INDEX
    Explanations

    special characters or symbols that might indicate formatting or coding elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ünk
    -0.20
    ük
    -0.19
    eko
    -0.18
    etz
    -0.17
    etc
    -0.17
    defgroup
    -0.17
    etus
    -0.17
    ets
    -0.17
    elian
    -0.16
    ofs
    -0.16
    POSITIVE LOGITS
    ket
    0.30
    bb
    0.29
    ink
    0.27
    kk
    0.27
    kn
    0.26
    kb
    0.26
    it
    0.25
    ine
    0.25
    kre
    0.25
    ivel
    0.24
    Act Density 0.004%

    No Known Activations