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

    Neuronpedia

    INDEX
    Explanations

    terms related to geometry and measurement, specifically surfaces with well-defined angles and stacks at various angles

    oai_token-act-pair · gpt-3.5-turbo

    technical descriptions and classifications of physical substances or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SPORTS
    -0.68
     Lyft
    -0.67
    anamo
    -0.66
     Emails
    -0.66
     Cabin
    -0.64
    PHOTOS
    -0.61
     Weekend
    -0.60
    POST
    -0.60
     Trailer
    -0.59
    BILL
    -0.59
    POSITIVE LOGITS
     respectively
    1.31
     apiece
    1.14
     varying
    1.13
     respective
    1.05
     overlapping
    1.03
     differing
    1.01
     each
    0.97
     overlap
    0.96
     integers
    0.94
     contiguous
    0.92
    Act Density 0.686%

    No Known Activations