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

    Neuronpedia

    INDEX
    Explanations

    the use of the word "well" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exactly
    -0.16
    rina
    -0.15
    Z
    -0.14
    976
    -0.14
    ast
    -0.14
    avia
    -0.14
    776
    -0.13
    yan
    -0.13
     U
    -0.13
    ight
    -0.13
    POSITIVE LOGITS
    tü
    0.18
    bos
    0.16
    interop
    0.14
     THPT
    0.14
    izons
    0.14
    Interop
    0.14
    izzas
    0.14
    úsqueda
    0.14
    ThanOr
    0.14
    tura
    0.14
    Act Density 0.020%

    No Known Activations