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

    Neuronpedia

    INDEX
    Explanations

    discussions or references to evaluating or answering complex questions and results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    '
    -0.46
    yo
    -0.45
     ber
    -0.45
    ’
    -0.43
    in
    -0.39
     and
    -0.38
    ren
    -0.38
    Kk
    -0.37
    ..
    -0.37
     gj
    -0.37
    POSITIVE LOGITS
     EconPapers
    0.98
    StructEnd
    0.90
     esternos
    0.88
     InputDecoration
    0.87
    principalColumn
    0.86
     Anſ
    0.85
    verwijspagina
    0.84
    +:+
    0.82
     Efq
    0.80
    ✭✭
    0.80
    Act Density 1.134%

    No Known Activations