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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of disambiguation or clarification in text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    gameserver
    -0.66
     triển
    -0.56
     yeti
    -0.47
    lico
    -0.43
    ullah
    -0.43
    ospel
    -0.43
    irs
    -0.42
     escala
    -0.42
     υ
    -0.42
    healthy
    -0.41
    POSITIVE LOGITS
    disambiguation
    2.00
    ambiguation
    1.16
    verwijspagina
    1.09
     ujednoznacz
    1.08
    homonymie
    0.90
    rungsseite
    0.89
    MemoryWarning
    0.88
    曖昧さ回避
    0.87
    AxisAlignment
    0.86
    DeleteBehavior
    0.83
    Act Density 0.000%

    No Known Activations