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

    Neuronpedia

    INDEX
    Explanations

    instances of document structure or formatting tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GEBURTS
    -0.97
     myſelf
    -0.97
    tvguidetime
    -0.89
    TagMode
    -0.85
     fevere
    -0.84
     aDecoder
    -0.81
    expandindo
    -0.80
    imetsu
    -0.79
     Jefus
    -0.78
     Efq
    -0.78
    POSITIVE LOGITS
     and
    0.62
     The
    0.56
     if
    0.50
     also
    0.46
     And
    0.45
     is
    0.44
     &
    0.44
    .
    0.43
     a
    0.43
     …
    0.42
    Act Density 0.007%

    No Known Activations