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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "which" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    trag
    -0.17
    ussen
    -0.15
    fü
    -0.15
    ستÙħ
    -0.15
    reta
    -0.15
    itele
    -0.15
    MAND
    -0.15
    üssen
    -0.14
    rag
    -0.14
    ugin
    -0.14
    POSITIVE LOGITS
     im
    0.16
    weise
    0.14
     latter
    0.14
     Pont
    0.14
    oice
    0.14
     Maxwell
    0.13
     Penn
    0.13
     pocket
    0.13
    endon
    0.13
    ÑĢави
    0.13
    Act Density 0.092%

    No Known Activations