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

    Neuronpedia

    INDEX
    Explanations

    descriptions of types of personnel, likely in a professional context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ftu
    -1.30
     fep
    -1.29
     effe
    -1.27
     increa
    -1.26
     mef
    -1.25
     aen
    -1.25
     volunte
    -1.25
     affez
    -1.23
     fta
    -1.23
     fup
    -1.20
    POSITIVE LOGITS
     who
    0.92
     whom
    0.81
    who
    0.75
     whose
    0.72
     from
    0.70
     الذين
    0.66
     Who
    0.64
     willing
    0.64
    hips
    0.63
    Who
    0.62
    Act Density 0.517%

    No Known Activations