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

    Neuronpedia

    INDEX
    Explanations

    the word "This" at the beginning of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce statements or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Constantin
    -0.59
     goto
    -0.54
     snipp
    -0.53
     Oo
    -0.53
    aiman
    -0.53
     MIA
    -0.52
     Becker
    -0.52
     Vita
    -0.52
     xp
    -0.52
     etc
    -0.51
    POSITIVE LOGITS
    [/
    1.19
    resa
    0.94
    âĢ
    0.92
    .""
    0.87
    %"
    0.83
    DonaldTrump
    0.80
    withstanding
    0.80
    usterity
    0.79
    ]'
    0.78
    ¨
    0.78
    Act Density 0.269%

    No Known Activations