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

    Neuronpedia

    INDEX
    Explanations

    references to letters and letter-writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yan
    -0.17
    yum
    -0.17
    yor
    -0.16
    onet
    -0.16
    andle
    -0.15
    emaker
    -0.15
    yon
    -0.15
    zdy
    -0.15
    vier
    -0.15
    slu
    -0.15
    POSITIVE LOGITS
    press
    0.28
    head
    0.24
    atura
    0.21
    ed
    0.20
    ing
    0.20
    -spacing
    0.19
     addressed
    0.19
    ewe
    0.18
    heads
    0.17
     opener
    0.17
    Act Density 0.026%

    No Known Activations