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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases and references to similarity between methods or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    similar to or comparable with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     WID
    -0.45
    httphttps
    -0.41
     maga
    -0.41
    ennom
    -0.39
    lian
    -0.38
    WID
    -0.38
    copo
    -0.38
    opo
    -0.38
    mero
    -0.38
    miti
    -0.37
    POSITIVE LOGITS
    ніципалі
    0.56
     contextLoads
    0.54
     EconPapers
    0.52
    AddTagHelper
    0.50
     CURIAM
    0.49
    tagHelperRunner
    0.49
    BufferException
    0.48
    OrEqual
    0.46
     betweenstory
    0.45
    RTCF
    0.45
    Act Density 0.110%

    No Known Activations