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

    Neuronpedia

    INDEX
    Explanations

    references to letters and related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yan
    -0.19
    yon
    -0.18
    yum
    -0.16
     letters
    -0.16
    onet
    -0.16
     letter
    -0.16
     бÑĥк
    -0.16
    sale
    -0.15
    emaker
    -0.15
    sid
    -0.15
    POSITIVE LOGITS
    press
    0.27
    head
    0.21
    atura
    0.21
    ìĹ´
    0.19
    ed
    0.18
    -spacing
    0.18
    olem
    0.17
    ing
    0.17
    red
    0.16
    winner
    0.16
    Act Density 0.024%

    No Known Activations