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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by determiners

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     rhy
    -0.22
     sow
    -0.21
     Expect
    -0.19
     thence
    -0.19
    Stage
    -0.19
     practicable
    -0.19
    =-=-=-=-=-=-=-=-
    -0.18
    ONSORED
    -0.18
     naming
    -0.18
    gyn
    -0.18
    POSITIVE LOGITS
    ifice
    0.25
    ructose
    0.24
    ggles
    0.23
    ographies
    0.22
    sbm
    0.22
    ournals
    0.22
    urga
    0.22
    rogram
    0.22
    anked
    0.22
    untled
    0.21
    Act Density 0.071%

    No Known Activations