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

    Neuronpedia

    INDEX
    Explanations

    expressions of understanding and perspectives on complex situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unken
    -0.17
    kins
    -0.15
    anou
    -0.15
    kers
    -0.15
    eur
    -0.15
    ÏĮÏģ
    -0.15
    odi
    -0.14
    undry
    -0.14
    ely
    -0.14
     worm
    -0.14
    POSITIVE LOGITS
    /cal
    0.15
    cho
    0.15
    ouble
    0.15
    636
    0.14
    afil
    0.14
    arg
    0.14
     cargo
    0.14
     tat
    0.13
    ahlen
    0.13
     why
    0.13
    Act Density 0.069%

    No Known Activations