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

    Neuronpedia

    INDEX
    Explanations

    elements that indicate procedural context or methodology in scientific writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.95
     Anſ
    -0.89
    istoitu
    -0.88
    twimg
    -0.87
     Monfieur
    -0.87
     chofe
    -0.86
     iſt
    -0.86
     Theſe
    -0.84
    Rüyada
    -0.84
    BibitemShut
    -0.83
    POSITIVE LOGITS
     and
    1.03
     in
    0.82
     or
    0.80
    ,
    0.78
     which
    0.72
     of
    0.72
     to
    0.69
     on
    0.69
     at
    0.66
     with
    0.65
    Act Density 0.464%

    No Known Activations