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

    Neuronpedia

    INDEX
    Explanations

    concepts and terms related to similarity and equality

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

    "... same ... as" construction

    np_acts-logits-general · gemini-2.0-flash

    sameness and similarity comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дописавши
    -1.15
     kasarigan
    -0.99
     kaarangay
    -0.95
    GraphicsUnit
    -0.93
    yntaxException
    -0.92
    Izvori
    -0.91
    脚注の使い方
    -0.88
    principalTable
    -0.87
    RenderAtEndOf
    -0.86
    homonymie
    -0.84
    POSITIVE LOGITS
     than
    1.29
     as
    1.06
     kuin
    1.03
     THAN
    0.70
     that
    0.64
    than
    0.63
     same
    0.63
    same
    0.62
     wie
    0.58
    Same
    0.55
    Act Density 0.275%

    No Known Activations