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

    Neuronpedia

    INDEX
    Explanations

    references to authority and governance structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃŃch
    -0.16
    à¥Ģद
    -0.15
    ************************************************
    -0.14
     Gesture
    -0.14
    uetype
    -0.14
    ë¥
    -0.14
     Evel
    -0.14
    ｡
    -0.14
    idf
    -0.14
    ivre
    -0.13
    POSITIVE LOGITS
     ausp
    0.46
     umbrella
    0.40
     guise
    0.37
     banner
    0.34
     guidance
    0.33
     supervision
    0.33
     tut
    0.33
     direction
    0.31
     heading
    0.31
     circumstances
    0.31
    Act Density 0.088%

    No Known Activations