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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isbury
    -0.07
    edes
    -0.07
    è©
    -0.07
     Ekon
    -0.07
    leurs
    -0.07
     single
    -0.06
    arro
    -0.06
    ISTRIBUT
    -0.06
     armed
    -0.06
    UnderTest
    -0.06
    POSITIVE LOGITS
    /File
    0.07
    apis
    0.07
    aida
    0.06
    kel
    0.06
    zer
    0.06
    ̣
    0.06
    ungen
    0.06
     (*((
    0.06
    AP
    0.06
     safeg
    0.06
    Act Density 0.002%

    No Known Activations