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

    Neuronpedia

    INDEX
    Explanations

    references to numbers or quantitative information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     poliester
    -1.01
     lele
    -0.89
     gend
    -0.89
     meras
    -0.87
     sement
    -0.86
     cyr
    -0.86
     augus
    -0.85
     parati
    -0.85
     poliuret
    -0.85
     ohr
    -0.82
    POSITIVE LOGITS
     shenan
    0.95
     unspeak
    0.89
     prolly
    0.87
     horrend
    0.87
     unavoid
    0.85
     intersper
    0.84
     encomp
    0.83
     indestru
    0.81
     needn
    0.79
     laug
    0.79
    Act Density 0.247%

    No Known Activations