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

    Neuronpedia

    INDEX
    Explanations

    statistics and numbers related to viewership or numerical data

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    uci
    -0.56
    Iterator
    -0.56
    IFA
    -0.55
     Luffy
    -0.53
    ESPN
    -0.52
    wd
    -0.52
    AH
    -0.52
     Glac
    -0.52
    !!
    -0.52
     Albania
    -0.51
    POSITIVE LOGITS
     latter
    1.24
     same
    1.11
     aforementioned
    1.09
     latest
    1.03
     entirety
    1.01
     slightest
    1.01
     remainder
    0.97
     entire
    0.93
     widest
    0.92
     ensuing
    0.92
    Act Density 2.984%

    No Known Activations