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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols or variables used in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ^{
    -0.83
    StructEnd
    -0.80
     ivelany
    -0.72
    قایناق‌لار
    -0.71
    twimg
    -0.67
    Према
    -0.65
    FunctionFlags
    -0.65
    Dzi
    -0.63
    StoryboardSegue
    -0.62
     שוליים
    -0.61
    POSITIVE LOGITS
    <sub>
    2.84
    $_
    1.22
     $_{\
    1.02
    $_{
    0.97
    }_{
    0.96
     $_{
    0.95
    <s>
    0.88
    }_{\
    0.88
     }_{\
    0.86
     }_{
    0.84
    Act Density 0.145%

    No Known Activations