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

    Neuronpedia

    INDEX
    Explanations

    terms related to neuroscience and socio-political topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     in
    -0.77
     at
    -0.75
     близь
    -0.75
     розта
    -0.74
     of
    -0.74
     to
    -0.71
     or
    -0.71
     is
    -0.70
     зберіга
    -0.70
     as
    -0.70
    POSITIVE LOGITS
     sappi
    1.77
     dises
    1.73
     abnorm
    1.72
     affez
    1.71
     abbra
    1.68
     dispen
    1.68
     ritard
    1.67
     nece
    1.65
     pessi
    1.64
     effe
    1.64
    Act Density 0.168%

    No Known Activations