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

    Neuronpedia

    INDEX
    Explanations

    instances of high-impact or prioritized phrases and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eeper
    -0.20
    elay
    -0.18
    elve
    -0.15
    æķ·
    -0.15
    ieval
    -0.15
     bob
    -0.14
    pekt
    -0.14
    errupt
    -0.14
    /application
    -0.14
     Cros
    -0.14
    POSITIVE LOGITS
    URA
    0.17
    ura
    0.17
    uras
    0.16
    uze
    0.15
    Ïĥη
    0.15
    ilestone
    0.14
    inus
    0.14
     Mile
    0.14
    797
    0.14
    æŃ£
    0.14
    Act Density 0.003%

    No Known Activations