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

    Neuronpedia

    INDEX
    Explanations

    specific numeric values or unique identifiers present in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hra
    -0.15
    rud
    -0.14
    ÑĢажд
    -0.14
    edir
    -0.14
    utzer
    -0.14
     zaj
    -0.14
    едагог
    -0.13
    enson
    -0.13
    ragen
    -0.13
     Tactics
    -0.13
    POSITIVE LOGITS
     Washington
    0.20
     Putin
    0.16
    Washington
    0.16
    ekk
    0.16
    porno
    0.16
    Putin
    0.15
     Amerikan
    0.15
     behalf
    0.15
     resurrect
    0.15
     pres
    0.14
    Act Density 0.002%

    No Known Activations