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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that denote significant metrics or indicators, particularly in academic or analytical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃŃo
    -0.16
     waivers
    -0.15
    окон
    -0.15
    acket
    -0.15
    quat
    -0.14
     Bett
    -0.14
    hetto
    -0.14
     derece
    -0.14
    ackets
    -0.14
    .Void
    -0.14
    POSITIVE LOGITS
    lish
    0.16
    Digest
    0.16
     Exp
    0.16
    uto
    0.16
    BA
    0.15
     active
    0.15
    UTO
    0.15
     cut
    0.15
    lab
    0.15
     bif
    0.15
    Act Density 0.017%

    No Known Activations