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

    Neuronpedia

    INDEX
    Explanations

    statements or inquiries prompting reflection or action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "U" followed by a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utterstock
    -0.71
     disse
    -0.68
     basics
    -0.66
    ãĤ©
    -0.62
    ãĤ¨ãĥ«
    -0.61
     browsing
    -0.61
    olis
    -0.61
     srfAttach
    -0.60
    ãĥ¼ãĥĨãĤ£
    -0.59
    redients
    -0.59
    POSITIVE LOGITS
    S
    0.86
     Soccer
    0.80
    $.
    0.76
     Geological
    0.73
    Va
    0.73
    N
    0.70
     Embassy
    0.70
     Nations
    0.70
     Pact
    0.67
    government
    0.67
    Act Density 0.049%

    No Known Activations