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

    Neuronpedia

    INDEX
    Explanations

    commonly occurring patterns in text data, particularly the sequence "ik" followed by a single character

    oai_token-act-pair · gpt-3.5-turbo

    the mention of specific names and terms associated with the "Balik Scientist" program

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FFFF
    -0.74
     Winchester
    -0.64
     halves
    -0.62
     equivalents
    -0.62
    Steam
    -0.61
    mpeg
    -0.61
    DIT
    -0.60
     vested
    -0.58
     poppy
    -0.57
    birth
    -0.57
    POSITIVE LOGITS
    achu
    1.24
    ernels
    1.07
    yu
    1.07
    ernel
    1.06
    ileaks
    1.01
    rish
    0.97
    owski
    0.97
    atana
    0.95
    istan
    0.95
    hs
    0.95
    Act Density 0.022%

    No Known Activations