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

    Neuronpedia

    INDEX
    Explanations

    technical or programming jargon

    oai_token-act-pair · gpt-3.5-turbo

    tense and aspectual variations in verbs within complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Colleges
    -0.53
     Mormons
    -0.48
    htaking
    -0.47
     Tours
    -0.47
    Newsletter
    -0.46
     occupations
    -0.46
     Canaver
    -0.46
     DeVos
    -0.45
     Mississippi
    -0.45
     astonished
    -0.45
    POSITIVE LOGITS
    Firstly
    0.56
     comprom
    0.54
    ICO
    0.54
    «ĺ
    0.53
     anyways
    0.53
    £ı
    0.52
    >.
    0.51
    !).
    0.51
    Lear
    0.51
    Discuss
    0.50
    Act Density 1.536%

    No Known Activations