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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases ending with a period

    oai_token-act-pair · gpt-3.5-turbo

    periods indicating the end of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     concess
    -0.77
     divest
    -0.75
     clandestine
    -0.72
     tricked
    -0.72
     organised
    -0.71
     ejected
    -0.71
     authorised
    -0.70
     broker
    -0.70
     extinguished
    -0.70
     magistrate
    -0.70
    POSITIVE LOGITS
    âĢ
    1.95
    âĸ
    1.36
     âĢ
    1.36
    âĸł
    1.30
    âľ
    1.30
    âĿ
    1.27
    âĢł
    1.27
     âĸ
    1.23
    ¶
    1.22
    Anyway
    1.21
    Act Density 0.492%

    No Known Activations