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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and expressions related to scientific or technical content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.93
     esternos
    -0.91
     estekak
    -0.90
    expandindo
    -0.89
     autorytatywna
    -0.84
    <unused41>
    -0.81
    <unused28>
    -0.80
    <unused51>
    -0.80
    <unused14>
    -0.80
    [@BOS@]
    -0.80
    POSITIVE LOGITS
    ↵↵
    0.36
    And
    0.34
    .
    0.31
     meanwhile
    0.30
    ness
    0.30
     as
    0.30
     
    0.29
     Zust
    0.29
    1
    0.29
     which
    0.29
    Act Density 1.102%

    No Known Activations