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

    Neuronpedia

    INDEX
    Explanations

    the word "pat" followed by varying numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "pattern" or "patterning."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sson
    -0.73
     2021
    -0.72
     Dynamics
    -0.72
    akers
    -0.71
    effective
    -0.68
    ISON
    -0.67
    iga
    -0.67
    ceiver
    -0.67
     Electronics
    -0.66
     2022
    -0.65
    POSITIVE LOGITS
     pat
    4.09
    pat
    1.63
     Pat
    1.37
    Pat
    1.26
     rub
    1.13
     PAT
    1.12
     patron
    1.10
     blat
    0.99
     pap
    0.98
     palp
    0.95
    Act Density 0.021%

    No Known Activations