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

    Neuronpedia

    INDEX
    Explanations

    mentions of mirrors and their properties or effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    первых
    -0.73
     leeftijd
    -0.69
    uesia
    -0.68
    OfYear
    -0.68
    dawg
    -0.67
    :]:
    -0.64
    MMdd
    -0.64
    ientôt
    -0.64
     hendak
    -0.63
    chargez
    -0.62
    POSITIVE LOGITS
     mirror
    2.48
     mirrors
    2.36
     Mirror
    2.35
     Mirrors
    2.22
    Mirror
    2.10
     MIRROR
    2.06
    mirror
    2.05
    Mirrors
    1.98
     mirrored
    1.74
     mirroring
    1.70
    Act Density 0.060%

    No Known Activations