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

    Neuronpedia

    INDEX
    Explanations

    terms related to completion and finished products

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

    finished product

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ché
    -0.38
     quia
    -0.35
    fowl
    -0.35
    lain
    -0.35
    kin
    -0.34
    ougars
    -0.33
    stock
    -0.33
    ColumnHeader
    -0.32
    ilen
    -0.32
    Syn
    -0.32
    POSITIVE LOGITS
     finished
    0.72
     completed
    0.63
    仕上が
    0.62
     Finished
    0.60
    成品
    0.59
    finished
    0.58
    SBATCH
    0.56
     fertig
    0.56
    EndTag
    0.56
     finishing
    0.55
    Act Density 0.105%

    No Known Activations