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

    Neuronpedia

    INDEX
    Explanations

    terms related to recognition and accolades, particularly in creative fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istrovstvÃŃ
    -0.17
    ниÑĨÑı
    -0.17
     ActionTypes
    -0.17
    nodoc
    -0.17
    illow
    -0.17
    cente
    -0.16
     Clips
    -0.15
     Ðļал
    -0.15
    isd
    -0.15
    UCE
    -0.15
    POSITIVE LOGITS
     j
    0.16
     already
    0.15
    279
    0.15
     I
    0.15
     P
    0.15
     ge
    0.15
     b
    0.15
     B
    0.14
     bas
    0.14
     Middle
    0.14
    Act Density 0.358%

    No Known Activations