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

    Neuronpedia

    INDEX
    Explanations

    references to labels in programming or data structure contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     />";
    -0.87
    ")));
    -0.86
    "]));
    -0.84
     htons
    -0.83
     Pizarro
    -0.79
     ſt
    -0.78
     $_"
    -0.78
     ProductService
    -0.77
    ."));
    -0.76
    είται
    -0.75
    POSITIVE LOGITS
     label
    1.86
     labels
    1.86
     Label
    1.79
    labels
    1.73
     Labels
    1.70
     LABEL
    1.69
    label
    1.65
    Labels
    1.62
    LABEL
    1.59
    Label
    1.54
    Act Density 0.060%

    No Known Activations