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

    Neuronpedia

    INDEX
    Explanations

    references to measurements or dimensions in technical descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trained
    -0.98
     certified
    -0.95
     qualified
    -0.84
     Certified
    -0.83
    trained
    -0.79
    Certified
    -0.79
     skilled
    -0.78
    certified
    -0.77
    Trained
    -0.75
     Trained
    -0.74
    POSITIVE LOGITS
    KommentareTeilen
    0.63
    ″
    0.57
    XmlAccessType
    0.56
     `"
    0.52
     inch
    0.51
     <=",
    0.50
    inch
    0.49
    ＂
    0.49
     inconn
    0.49
     <",
    0.49
    Act Density 0.211%

    No Known Activations