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

    Neuronpedia

    INDEX
    Explanations

    phrases related to names of people

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     unspeak
    -1.07
     gaily
    -0.97
     increa
    -0.96
     shenan
    -0.96
     apprehen
    -0.95
     indescri
    -0.94
     assailed
    -0.86
     vainly
    -0.85
     disagre
    -0.85
     unavoid
    -0.84
    POSITIVE LOGITS
     Jim
    1.56
    Jim
    1.55
    JIM
    1.26
     jim
    1.24
     JIM
    1.21
    jim
    1.17
    James
    0.75
     Jimenez
    0.73
     James
    0.73
     Jiménez
    0.72
    Act Density 0.055%

    No Known Activations