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

    Neuronpedia

    INDEX
    Explanations

    specific locations within a building, particularly rooms

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of rooms and spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oÄŁ
    -0.63
     Democrat
    -0.61
    Doctors
    -0.59
     Falk
    -0.57
    Hur
    -0.56
    BI
    -0.56
    Leader
    -0.55
     Physicians
    -0.54
    rawdownloadcloneembedreportprint
    -0.53
     surrogate
    -0.53
    POSITIVE LOGITS
    paces
    1.47
    mith
    1.44
    pace
    1.42
    hips
    1.41
    hops
    1.37
    poons
    1.36
    hip
    1.31
    etting
    1.31
    creen
    1.24
    pring
    1.22
    Act Density 0.156%

    No Known Activations