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

    Neuronpedia

    INDEX
    Explanations

    names of individuals mentioned in a text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ":"/
    -0.70
    imester
    -0.67
    ÙIJ
    -0.64
     endeavor
    -0.63
    ocial
    -0.62
    ":-
    -0.61
    =\"
    -0.61
    conom
    -0.60
    xual
    -0.60
     mistakenly
    -0.59
    POSITIVE LOGITS
     etc
    1.34
    etc
    1.08
     Seym
    0.95
     Jr
    0.92
     Sof
    0.84
     et
    0.83
     Lenn
    0.83
     Moroc
    0.82
     Samoa
    0.81
     Rox
    0.80
    Act Density 0.255%

    No Known Activations