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

    Neuronpedia

    INDEX
    Explanations

    various types of labels or identifiers used in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     />";
    -0.85
    ")));
    -0.82
     htons
    -0.79
    "]));
    -0.78
    Читайте
    -0.75
     ProductService
    -0.72
    είται
    -0.72
     Pizarro
    -0.71
     ſt
    -0.70
    =?";
    -0.70
    POSITIVE LOGITS
     labels
    1.66
     label
    1.66
     Label
    1.60
    labels
    1.56
     LABEL
    1.54
     Labels
    1.53
    Labels
    1.47
    label
    1.47
    LABEL
    1.45
    Label
    1.33
    Act Density 0.069%

    No Known Activations