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

    Neuronpedia

    INDEX
    Explanations

    universities or academic institutions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     overcrow
    -1.16
     moistened
    -1.05
     intersper
    -1.03
     disreg
    -1.01
     tupperware
    -0.94
     lmfao
    -0.94
     friable
    -0.94
     subgoals
    -0.92
     cushi
    -0.91
     shenan
    -0.89
    POSITIVE LOGITS
     alkoh
    1.69
     kosme
    1.67
     silikon
    1.59
     makro
    1.52
     keramik
    1.51
     antik
    1.48
     kön
    1.46
     akut
    1.45
     kompati
    1.44
     minimalis
    1.44
    Act Density 0.061%

    No Known Activations