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

    Neuronpedia

    INDEX
    Explanations

    the beginning of sentences or paragraphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ...");
    -0.59
    %@",
    -0.57
    jerg
    -0.57
    outre
    -0.56
    )";
    -0.55
     Cuban
    -0.54
    de
    -0.54
    getAttributes
    -0.54
    ite
    -0.54
     Rote
    -0.53
    POSITIVE LOGITS
    DeleteCommand
    0.82
    saraba
    0.81
    AddTagHelper
    0.81
     auroit
    0.80
    GHIJKLM
    0.79
    TagHelper
    0.79
     avoient
    0.77
     feroit
    0.76
     hiér
    0.74
     تانيه
    0.74
    Act Density 0.277%

    No Known Activations