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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of "where" or location in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iven
    -0.17
    CTS
    -0.16
     Jud
    -0.15
    itan
    -0.15
    prus
    -0.15
    ouv
    -0.14
    erson
    -0.14
     Leer
    -0.14
     ãĢ
    -0.13
    Press
    -0.13
    POSITIVE LOGITS
    wise
    0.17
    inta
    0.15
     Watkins
    0.14
    ENSE
    0.14
    dob
    0.14
    wis
    0.13
     fucking
    0.13
    اا
    0.13
    bout
    0.13
    /ex
    0.13
    Act Density 0.019%

    No Known Activations