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

    Neuronpedia

    INDEX
    Explanations

    facts or events related to specific occurrences, projects or influential individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     apprehen
    -1.06
     disagre
    -1.01
     maksi
    -0.96
     unspeak
    -0.95
     reluct
    -0.91
     intrigu
    -0.86
     vainly
    -0.86
     inappro
    -0.85
     uninten
    -0.84
     attemp
    -0.83
    POSITIVE LOGITS
     so
    0.83
    so
    0.75
    wieś
    0.72
     SO
    0.68
     constate
    0.66
    @[+][
    0.65
    astéro
    0.63
    loài
    0.63
    Viitteet
    0.61
    So
    0.61
    Act Density 0.075%

    No Known Activations