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

    Neuronpedia

    INDEX
    Explanations

    statements and opinions expressed in a formal or political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ults
    -0.17
    AreaView
    -0.15
     Lite
    -0.15
     removeObject
    -0.14
    ENTE
    -0.14
    ysa
    -0.14
    EMON
    -0.14
    IRA
    -0.14
    mrt
    -0.14
     Woche
    -0.14
    POSITIVE LOGITS
    chin
    0.18
     Fry
    0.15
    æĪij
    0.14
    [*
    0.14
     Suff
    0.13
    ÏģÏħ
    0.13
    devil
    0.13
    unny
    0.13
    plural
    0.13
    actable
    0.13
    Act Density 0.216%

    No Known Activations