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

    Neuronpedia

    INDEX
    Explanations

    references to academic sources, specifically pertaining to theories and studies in a scholarly context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ropolis
    -0.17
    ibu
    -0.15
    ertino
    -0.15
    ãĤ¤ãĤ¯
    -0.15
    ulado
    -0.15
    orget
    -0.14
    hol
    -0.14
    ãģĸ
    -0.14
     zas
    -0.14
    occo
    -0.14
    POSITIVE LOGITS
    LAY
    0.20
     Bay
    0.20
    lay
    0.19
    ay
    0.18
    Bay
    0.17
    acy
    0.17
     Hay
    0.17
     Fay
    0.17
    ocy
    0.17
    Jay
    0.16
    Act Density 0.035%

    No Known Activations