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

    Neuronpedia

    INDEX
    Explanations

    specific declarative statements related to entities and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Thus
    -0.52
     thus
    -0.49
     significant
    -0.47
    Thus
    -0.46
    uce
    -0.46
    ence
    -0.45
     provided
    -0.43
    収録曲
    -0.42
    innan
    -0.41
     copias
    -0.41
    POSITIVE LOGITS
     GenerationType
    1.07
    DockStyle
    1.03
    Datuak
    0.95
     AssemblyCulture
    0.90
     transfieras
    0.87
    MLLoader
    0.87
    ⓧ
    0.85
    rungsseite
    0.82
     дописавши
    0.82
    ^(@)
    0.81
    Act Density 0.359%

    No Known Activations