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

    Neuronpedia

    INDEX
    Explanations

    references to formatting or structural elements, possibly indicating blocks of text or code

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.94
    BagLayout
    -0.79
     quadrangle
    -0.75
     ་་
    -0.75
     ―――――
    -0.74
    ResponseWriter
    -0.71
     Efq
    -0.71
     ========
    -0.71
    AxisAlignment
    -0.71
     {?}
    -0.71
    POSITIVE LOGITS
     an
    0.53
    +#+
    0.52
     process
    0.50
     
    0.45
     -
    0.44
      
    0.42
    sprozess
    0.42
     DR
    0.40
    <eos>
    0.40
     so
    0.39
    Act Density 0.026%

    No Known Activations