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

    Neuronpedia

    INDEX
    Explanations

    prominent dates and numerical values in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -digit
    -0.16
    usic
    -0.16
    ute
    -0.15
    rik
    -0.15
    rek
    -0.15
     appro
    -0.15
    ain
    -0.14
    +xml
    -0.14
    iy
    -0.14
    igit
    -0.14
    POSITIVE LOGITS
     -,
    0.16
    ima
    0.15
     -:
    0.14
    bos
    0.14
     tatto
    0.13
    cak
    0.13
    Beyond
    0.13
     -.
    0.13
    onda
    0.13
    bir
    0.13
    Act Density 0.072%

    No Known Activations