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

    Neuronpedia

    INDEX
    Explanations

    numbers and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    [
    -0.32
    but
    -0.29
    and
    -0.29
    viz
    -0.24
    s
    -0.24
    the
    -0.24
    in
    -0.23
    a
    -0.23
    i
    -0.23
     which
    -0.22
    POSITIVE LOGITS
    .,
    0.18
     ,
    0.17
    !,
    0.16
    gage
    0.16
    ?,
    0.16
    undefined
    0.16
    +,
    0.14
    tip
    0.14
     -
    0.14
    lab
    0.14
    Act Density 1.004%

    No Known Activations