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

    Neuronpedia

    INDEX
    Explanations

    words related to genetics, intelligence, and medical testing

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     menta
    -0.72
     purtroppo
    -0.72
     sappi
    -0.70
     poichè
    -0.70
     valla
    -0.66
     Anm
    -0.66
     saba
    -0.64
     hej
    -0.64
     anzi
    -0.63
     lomb
    -0.63
    POSITIVE LOGITS
     containing
    0.70
     incorporating
    0.64
     without
    0.60
     Containing
    0.60
     featuring
    0.59
    without
    0.56
     involving
    0.56
     backless
    0.53
     with
    0.53
     based
    0.53
    Act Density 0.859%

    No Known Activations