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

    Neuronpedia

    INDEX
    Explanations

    questions or requests for information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "asked" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vantage
    -0.62
    erno
    -0.62
    marine
    -0.61
    Ĥ¬
    -0.61
    Zone
    -0.56
    absor
    -0.56
    Fit
    -0.55
    MpServer
    -0.55
    etheless
    -0.53
     ESV
    -0.52
    POSITIVE LOGITS
     questions
    1.19
     whether
    0.99
     why
    0.94
     Questions
    0.89
    naires
    0.87
     forgiveness
    0.84
     question
    0.84
     pardon
    0.84
     about
    0.81
     to
    0.81
    Act Density 0.030%

    No Known Activations