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

    Neuronpedia

    INDEX
    Explanations

    questions about various topics

    oai_token-act-pair · gpt-3.5-turbo

    questions and inquiries about experiences or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     downstream
    -0.81
     invisible
    -0.74
     stret
    -0.73
     wagon
    -0.72
     migr
    -0.71
     dumping
    -0.70
     dumped
    -0.70
     upstream
    -0.69
     displaced
    -0.68
     cures
    -0.68
    POSITIVE LOGITS
    Answer
    1.33
    Absolutely
    0.92
    RM
    0.90
    Yes
    0.90
    Question
    0.89
    ccording
    0.89
    Interview
    0.88
    OVA
    0.88
    Tell
    0.87
    ItemImage
    0.87
    Act Density 0.135%

    No Known Activations