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
    sizeCache
    -0.78
    GraphicsUnit
    -0.74
     rospy
    -0.64
     GoogleFonts
    -0.64
    colgroup
    -0.63
    uxxxx
    -0.63
     BoxFit
    -0.60
    脚注の使い方
    -0.59
    FXML
    -0.59
    WriteTagHelper
    -0.58
    POSITIVE LOGITS
     is
    0.62
     lasted
    0.59
    [])
    0.58
     represents
    0.57
     was
    0.57
     brings
    0.55
    したのは
    0.54
    брь
    0.53
    들은
    0.53
     allows
    0.53
    Act Density 0.879%

    No Known Activations