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

    Neuronpedia

    INDEX
    Explanations

    sentences ending in full stops

    oai_token-act-pair · gpt-3.5-turbo

    sentences ending with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unpop
    -0.68
     stamped
    -0.67
    oton
    -0.66
     optional
    -0.64
     antigen
    -0.64
    erers
    -0.63
     parameter
    -0.63
    grain
    -0.63
     gut
    -0.63
    ters
    -0.62
    POSITIVE LOGITS
     Additionally
    1.21
     His
    1.21
     Along
    1.13
     During
    1.08
     However
    1.08
     He
    1.05
     Recently
    1.02
     Known
    1.01
     Nevertheless
    1.01
     Married
    1.00
    Act Density 0.429%

    No Known Activations