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

    Neuronpedia

    INDEX
    Explanations

    uppercase letters that appear in the form of special characters

    oai_token-act-pair · gpt-3.5-turbo

    questions related to creative processes and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     downstream
    -0.89
     marked
    -0.69
     upstream
    -0.68
     vaccinated
    -0.63
     marks
    -0.63
     careless
    -0.63
     proud
    -0.62
     invisible
    -0.61
     restores
    -0.61
     migr
    -0.60
    POSITIVE LOGITS
    Answer
    1.23
    Absolutely
    0.90
    =-=-=-=-=-=-=-=-
    0.88
    Issue
    0.86
    Question
    0.85
     Answer
    0.82
    Yes
    0.81
    Yeah
    0.79
    YES
    0.78
    ccording
    0.77
    Act Density 0.190%

    No Known Activations