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

    Neuronpedia

    INDEX
    Explanations

    phrases related to using the internet for educational and professional resources

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific token markers indicating the beginning or end of text segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itia
    -0.73
    --+
    -0.63
    Cho
    -0.62
    ONSORED
    -0.62
    soever
    -0.62
    izes
    -0.62
    oe
    -0.62
    esar
    -0.61
    #$
    -0.61
    htar
    -0.60
    POSITIVE LOGITS
     sake
    1.62
     foreseeable
    1.42
     purposes
    1.27
     unin
    1.23
     longest
    1.16
     moment
    1.13
     meantime
    1.01
     past
    1.01
     duration
    1.00
     remainder
    0.99
    Act Density 0.066%

    No Known Activations