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

    Neuronpedia

    INDEX
    Explanations

    non-standard or playful representations of language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (æľ¨
    -0.17
    ipa
    -0.16
    (æĹ¥
    -0.15
    (æ°´
    -0.15
     Oc
    -0.14
    tractive
    -0.14
    IDE
    -0.14
    phem
    -0.14
    Leaf
    -0.14
     svÄĽ
    -0.14
    POSITIVE LOGITS
    323
    0.16
     tents
    0.15
    ãĥ§
    0.15
    utterstock
    0.15
    mma
    0.14
    odge
    0.14
    orsk
    0.14
    amik
    0.14
    Ñĩно
    0.14
    ,uint
    0.14
    Act Density 0.016%

    No Known Activations