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

    Neuronpedia

    INDEX
    Explanations

    proper names or words related to specific events or locations, particularly those ending with "ay"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ay."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CNS
    -0.71
     lif
    -0.68
     class
    -0.65
     Rings
    -0.65
     flu
    -0.64
     Organ
    -0.64
     organ
    -0.64
     Const
    -0.62
     Virt
    -0.62
     REM
    -0.62
    POSITIVE LOGITS
    ay
    4.22
    ays
    2.49
    ayan
    2.25
    AY
    2.15
    ayed
    2.07
    aye
    2.05
    aying
    2.01
    aya
    1.98
    ayer
    1.69
    ayn
    1.55
    Act Density 0.015%

    No Known Activations