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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Of
    -0.19
     As
    -0.18
     At
    -0.18
     Along
    -0.18
     In
    -0.17
    Along
    -0.16
    #ad
    -0.16
     However
    -0.16
    ̧
    -0.16
    AtPath
    -0.15
    POSITIVE LOGITS
    ,
    0.24
    or
    0.20
    http
    0.19
    by
    0.19
    for
    0.18
    at
    0.17
    and
    0.17
    www
    0.17
    to
    0.16
    of
    0.16
    Act Density 0.831%

    No Known Activations