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

    Neuronpedia

    INDEX
    Explanations

    names of people or characters

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     seiz
    -0.48
    recated
    -0.47
     WARN
    -0.47
    adobe
    -0.47
    ãĤ°
    -0.46
     contrary
    -0.44
    benefit
    -0.43
     backlog
    -0.42
     surplus
    -0.42
     Latter
    -0.42
    POSITIVE LOGITS
     respectively
    1.29
     alike
    0.96
    kefeller
    0.68
     Jr
    0.68
    depending
    0.67
    ubi
    0.66
    both
    0.63
    zai
    0.61
    asions
    0.60
     LLP
    0.60
    Act Density 8.700%

    No Known Activations