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

    Neuronpedia

    INDEX
    Explanations

    specific references to entities or terms associated with a certain classification or identification system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.37
     imp
    -0.37
     TestBed
    -0.36
    ่า
    -0.35
    Introducing
    -0.35
     Disc
    -0.35
    umber
    -0.35
     îns
    -0.34
    ActionCreators
    -0.34
     explicit
    -0.34
    POSITIVE LOGITS
     estekak
    0.46
     चीज़ों
    0.42
    MemoryWarning
    0.41
    tvguidetime
    0.40
     esternos
    0.40
     <>",
    0.40
     pinulongan
    0.39
    ganu
    0.38
     ModelExpression
    0.38
     ſeveral
    0.38
    Act Density 0.380%

    No Known Activations