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

    Neuronpedia

    INDEX
    Explanations

    expressions of amazement or excitement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emean
    -0.17
    agna
    -0.15
     عاÙħØ©
    -0.15
    ì¶ľ
    -0.14
    ÑģÑĮ
    -0.14
    nech
    -0.13
    (éĩij
    -0.13
     cá»Ń
    -0.13
    ì°©
    -0.13
    jourd
    -0.13
    POSITIVE LOGITS
    zers
    0.33
    zer
    0.27
    za
    0.25
    ser
    0.23
    zas
    0.21
     another
    0.20
     talk
    0.19
     Factor
    0.19
    ow
    0.19
     indeed
    0.19
    Act Density 0.033%

    No Known Activations