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

    Neuronpedia

    INDEX
    Explanations

    end-of-turn markers in a conversation or interaction context

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

    code and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ----</
    -0.41
     argint
    -0.40
    oarece
    -0.40
     BoxDecoration
    -0.39
     &___
    -0.37
     étoit
    -0.36
     CanadaChoose
    -0.35
    ActionCreators
    -0.35
    modelBuilder
    -0.35
    astify
    -0.35
    POSITIVE LOGITS
    expandindo
    0.55
    swire
    0.47
    grà
    0.47
    dars
    0.47
     mostrarán
    0.47
     surla
    0.45
    piram
    0.45
    ineno
    0.44
     AssemblyTitle
    0.43
    laris
    0.43
    Act Density 0.005%

    No Known Activations