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

    Neuronpedia

    INDEX
    Explanations

    names of famous people who are being reported on

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -0.87
    accompan
    -0.85
     teasp
    -0.69
     transitioning
    -0.69
     DIRECT
    -0.66
     COM
    -0.66
     conserv
    -0.62
     carbohyd
    -0.62
     IMP
    -0.61
     parasitic
    -0.60
    POSITIVE LOGITS
    a
    1.33
    e
    1.22
    o
    1.17
    aq
    1.07
    y
    1.05
    al
    1.05
    ic
    1.05
    i
    1.01
    an
    1.00
    u
    0.98
    Act Density 0.184%

    No Known Activations