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

    Neuronpedia

    INDEX
    Explanations

    phrases that express intent or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -1.21
    AndEndTag
    -1.17
    ContentAsync
    -1.15
    RectangleBorder
    -1.14
    endphp
    -1.07
    ագրություններ
    -1.06
     AssemblyCulture
    -1.00
    abestanden
    -1.00
    PerformLayout
    -0.99
    ImageContext
    -0.98
    POSITIVE LOGITS
     is
    0.64
    :
    0.60
     She
    0.57
     
    0.57
    ,
    0.56
     The
    0.56
    ;
    0.54
     a
    0.53
    .
    0.52
     "
    0.51
    Act Density 0.156%

    No Known Activations