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

    Neuronpedia

    INDEX
    Explanations

    words related to axioms and things related to axes

    oai_token-act-pair · gpt-3.5-turbo

    references to "axioms" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ATURES
    -0.70
    creen
    -0.63
    ĨĴ
    -0.61
    FORMATION
    -0.61
     Columb
    -0.59
     bom
    -0.59
    ourage
    -0.59
     fry
    -0.57
    CLASSIFIED
    -0.57
     menstru
    -0.56
    POSITIVE LOGITS
    iom
    1.41
    illary
    1.17
    iop
    1.10
    alon
    1.04
    xon
    0.96
     ax
    0.91
    isy
    0.88
    ios
    0.88
    ansas
    0.88
    ical
    0.87
    Act Density 0.019%

    No Known Activations