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

    Neuronpedia

    INDEX
    Explanations

    technical or programming-related terms and structures in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (...)
    -0.19
     (('
    -0.17
     [âĢ¦]↵↵
    -0.16
    )(_
    -0.15
     («
    -0.15
     (${
    -0.13
     ('
    -0.13
     ${(
    -0.13
    .asInstanceOf
    -0.13
     ((_
    -0.12
    POSITIVE LOGITS
     [
    0.91
    [
    0.74
    _[
    0.61
    ,[
    0.57
    .[
    0.57
    -[
    0.54
    :[
    0.52
    ?[
    0.52
    }[
    0.50
    ][
    0.49
    Act Density 2.365%

    No Known Activations