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

    Neuronpedia

    INDEX
    Explanations

    information related to events or announcements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ell
    -0.64
     Burr
    -0.63
     Targ
    -0.62
     pist
    -0.61
     throats
    -0.61
     sockets
    -0.60
     footprints
    -0.59
     continents
    -0.58
     vel
    -0.58
    plings
    -0.58
    POSITIVE LOGITS
    themed
    1.19
    related
    1.13
    indust
    1.09
    induced
    1.06
    loving
    1.04
    oriented
    0.98
    policy
    0.96
    grade
    0.96
    based
    0.94
    driven
    0.94
    Act Density 0.058%

    No Known Activations