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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter 'a' across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AutoresizingMask
    -0.71
     يتيمه
    -0.68
    ly
    -0.67
    elly
    -0.65
     corrid
    -0.65
     abbildung
    -0.65
    ])->
    -0.64
     Handbuch
    -0.64
     diligen
    -0.64
    Portail
    -0.63
    POSITIVE LOGITS
    a
    2.50
    A
    1.61
    aA
    1.29
    getA
    1.02
    aR
    1.00
    aData
    0.97
    aS
    0.97
    aI
    0.94
    а
    0.93
    extAlignment
    0.90
    Act Density 0.222%

    No Known Activations