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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases and informal dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )::
    -0.15
    تش
    -0.15
    udden
    -0.14
    early
    -0.13
    UPDATED
    -0.13
    osci
    -0.13
    ãģ¾ãģļ
    -0.13
    abi
    -0.13
    first
    -0.13
    amedi
    -0.13
    POSITIVE LOGITS
     later
    0.33
     subsequently
    0.28
     subsequent
    0.27
    later
    0.26
    Later
    0.24
     thereafter
    0.23
     afterwards
    0.23
     Later
    0.23
     lesson
    0.22
     später
    0.20
    Act Density 0.310%

    No Known Activations