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

    Neuronpedia

    INDEX
    Explanations

    examples related to internet domains

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the sequence "eb" or references to related characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivities
    -0.83
     nomine
    -0.73
    ivity
    -0.71
    FTWARE
    -0.67
     latitude
    -0.67
    folk
    -0.65
    cross
    -0.65
     touch
    -0.64
     Ashe
    -0.64
    IVES
    -0.61
    POSITIVE LOGITS
    ruary
    1.32
    oard
    1.17
    uilt
    1.05
    acteria
    1.04
    rahim
    1.01
    edia
    0.98
    odies
    0.96
    anon
    0.95
    ulous
    0.94
    bled
    0.94
    Act Density 0.007%

    No Known Activations