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

    Neuronpedia

    INDEX
    Explanations

    special characters and punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    393
    -0.16
    hiro
    -0.15
    orgen
    -0.15
    ulet
    -0.14
    qua
    -0.14
    é«
    -0.14
    hiba
    -0.13
     defer
    -0.13
    Deferred
    -0.13
    é±
    -0.13
    POSITIVE LOGITS
    zin
    0.17
     Dün
    0.16
    (___
    0.16
    oce
    0.15
    (__
    0.15
    .__
    0.15
    (_)
    0.15
     Tunnel
    0.14
     rud
    0.14
     Purple
    0.14
    Act Density 0.002%

    No Known Activations