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

    Neuronpedia

    INDEX
    Explanations

    references to tours or touring activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <unused43>
    -1.14
    <unused14>
    -1.13
    <unused51>
    -1.13
    <unused79>
    -1.13
    <unused41>
    -1.13
    <unused3>
    -1.13
    <unused42>
    -1.13
    <unused74>
    -1.13
    <unused8>
    -1.13
    <unused16>
    -1.13
    POSITIVE LOGITS
     as
    0.68
     to
    0.59
     for
    0.59
     in
    0.57
     and
    0.57
    ,
    0.53
     it
    0.53
     from
    0.52
     Tour
    0.51
     =
    0.50
    Act Density 0.614%

    No Known Activations