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

    Neuronpedia

    INDEX
    Explanations

    references to the term "sag" or variations of it in various contexts

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

    words starting with sag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    THAN
    -0.42
    Atle
    -0.41
    entran
    -0.41
    anasia
    -0.41
    FX
    -0.40
     createTime
    -0.40
    NESSEE
    -0.39
     furi
    -0.38
    teni
    -0.38
    Than
    -0.37
    POSITIVE LOGITS
     Sag
    2.38
     sag
    2.28
    Sag
    2.19
    sag
    2.19
     SAG
    1.80
    SAG
    1.70
     sagging
    1.53
     sagit
    1.16
     Saginaw
    1.10
     Sagar
    1.08
    Act Density 0.004%

    No Known Activations