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

    Neuronpedia

    INDEX
    Explanations

    sentences where the speaker expresses uncertainty or seeks information

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty and mixed emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    surprisingly
    -0.67
     unsurprisingly
    -0.62
     predictably
    -0.59
    iannopoulos
    -0.55
    ãĥĥãĥĪ
    -0.54
     Cosponsors
    -0.53
    ortium
    -0.53
     ®
    -0.53
     similarly
    -0.52
    æ©Ł
    -0.52
    POSITIVE LOGITS
    ..."
    1.15
     âĢ¦"
    1.11
    )."
    1.09
     ..."
    1.08
    âĢ¦"
    1.07
    .")
    1.07
    .'"
    0.99
     fuckin
    0.98
    âĢ¦."
    0.97
    !'"
    0.93
    Act Density 1.484%

    No Known Activations