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

    Neuronpedia

    INDEX
    Explanations

    references to mirrors and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    первых
    -0.88
    chargez
    -0.75
     leeftijd
    -0.74
     Normdatei
    -0.71
    arakhand
    -0.68
    jme
    -0.64
    Kdo
    -0.64
    Ừ
    -0.64
    shund
    -0.63
     hvem
    -0.61
    POSITIVE LOGITS
     mirror
    2.06
     Mirror
    2.04
     Mirrors
    1.95
     mirrors
    1.93
     MIRROR
    1.81
    Mirror
    1.79
    Mirrors
    1.76
    mirror
    1.75
     mirroring
    1.49
     mirrored
    1.47
    Act Density 0.100%

    No Known Activations