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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax for template rendering

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Cleo
    -0.94
     Eud
    -0.80
     Neander
    -0.78
     Pizarro
    -0.75
     Ramona
    -0.74
     Solon
    -0.74
     Cæsar
    -0.73
     poffe
    -0.73
     raiſ
    -0.71
     Waray
    -0.71
    POSITIVE LOGITS
    {%
    1.58
     {%
    1.32
     CreateTagHelper
    0.69
    }{%
    0.69
     ProtoMessage
    0.68
     kasarigan
    0.66
    WriteByte
    0.64
    MLLoader
    0.58
     Byrd
    0.58
    ξύ
    0.58
    Act Density 0.001%

    No Known Activations