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

    Neuronpedia

    INDEX
    Explanations

    terms related to depth and penetration in scientific or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.70
    ViewFeatures
    -0.60
     Roskov
    -0.58
    IUrlHelper
    -0.58
    SourceChecksum
    -0.58
    allclose
    -0.57
     Geraadpleegd
    -0.55
     незавершена
    -0.55
    MemoryWarning
    -0.54
    Ծանոթ
    -0.54
    POSITIVE LOGITS
     deep
    2.13
     depth
    2.08
     deeper
    2.04
     depths
    1.97
     deepest
    1.88
    deep
    1.86
     Deeper
    1.84
     Depth
    1.79
    depth
    1.76
    Depth
    1.75
    Act Density 0.364%

    No Known Activations