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

    Neuronpedia

    INDEX
    Explanations

    structures related to mathematical matrices and formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     se
    -0.62
     
    -0.58
     de
    -0.57
     AS
    -0.56
     free
    -0.55
     sa
    -0.54
    <eos>
    -0.54
     x
    -0.54
     w
    -0.54
    Fermi
    -0.54
    POSITIVE LOGITS
     myſelf
    1.21
     itſelf
    1.03
     الحره
    1.02
    ConstraintMaker
    0.97
     дописавши
    0.97
     pleaſure
    0.97
     ſeveral
    0.96
    verwijspagina
    0.94
     raiſ
    0.93
     Efq
    0.92
    Act Density 0.063%

    No Known Activations