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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unsuccessfully
    -0.56
     Territory
    -0.56
     reb
    -0.56
     Syndicate
    -0.55
     tabs
    -0.54
     circles
    -0.53
     âĶľâĶĢâĶĢ
    -0.53
     Katrina
    -0.52
     scr
    -0.51
     competition
    -0.51
    POSITIVE LOGITS
    of
    3.88
    OF
    1.98
    ofer
    1.73
    oft
    1.68
    Of
    1.57
    oh
    1.33
    among
    1.28
    into
    1.23
    for
    1.19
    with
    1.16
    Act Density 0.012%

    No Known Activations