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

    Neuronpedia

    INDEX
    Explanations

    sections or headings labeled as "abstract" in academic documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ✭✭
    -0.60
    affaire
    -0.58
     vanden
    -0.57
     défa
    -0.56
    bootstrapcdn
    -0.55
    부
    -0.54
     Sleepy
    -0.54
    Ink
    -0.53
    readAs
    -0.51
     Ink
    -0.51
    POSITIVE LOGITS
    abstract
    1.15
     resourceCulture
    0.95
    AxisAlignment
    0.89
     חיצוניים
    0.87
    ViewHolder
    0.79
    swift
    0.73
    stdlib
    0.67
    exports
    0.65
    Swift
    0.64
     abstract
    0.64
    Act Density 0.021%

    No Known Activations