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

    Neuronpedia

    INDEX
    Explanations

    references to mirrors and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to mirrors and reflective surfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    первых
    -0.75
    shund
    -0.67
    Ừ
    -0.66
    chargez
    -0.66
     leeftijd
    -0.65
     FishBase
    -0.64
    žka
    -0.62
     Normdatei
    -0.60
     selanjutnya
    -0.59
     jongen
    -0.59
    POSITIVE LOGITS
     mirror
    2.17
     Mirror
    2.09
     mirrors
    2.06
     Mirrors
    1.98
     MIRROR
    1.89
    Mirror
    1.88
    Mirrors
    1.85
    mirror
    1.83
     mirrored
    1.59
     mirroring
    1.56
    Act Density 0.069%

    No Known Activations