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

    Neuronpedia

    INDEX
    Explanations

    references to written communications and official documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     announcements
    -0.16
    elen
    -0.16
     pl
    -0.15
    oki
    -0.15
    åłĤ
    -0.14
     vit
    -0.14
     disclosures
    -0.14
    hlas
    -0.13
     entering
    -0.13
     declaring
    -0.13
    POSITIVE LOGITS
     letter
    0.28
    letter
    0.24
     dated
    0.23
     Letter
    0.22
    dated
    0.21
    -letter
    0.21
     LETTER
    0.20
    (letter
    0.20
    Letter
    0.19
    _letter
    0.18
    Act Density 0.098%

    No Known Activations