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

    Neuronpedia

    INDEX
    Explanations

    pronouns referring to groups of people

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     monaster
    -0.89
     Singapur
    -0.88
     optik
    -0.83
     maksi
    -0.83
     Campionato
    -0.81
     poliuret
    -0.81
     parlamento
    -0.80
     antik
    -0.79
     meras
    -0.78
     lele
    -0.75
    POSITIVE LOGITS
     shenan
    0.91
     miscon
    0.82
    FTFY
    0.71
     intersper
    0.69
     indestru
    0.69
     unspeak
    0.67
    Rgds
    0.67
     mustn
    0.64
     sophistic
    0.63
     disagre
    0.63
    Act Density 0.374%

    No Known Activations