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

    Neuronpedia

    INDEX
    Explanations

    programming commands and configurations in a text document

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     grounding
    -0.73
     streng
    -0.73
     estimating
    -0.69
     affirm
    -0.69
     shedding
    -0.68
     unheard
    -0.67
     energ
    -0.67
     bour
    -0.66
     overlooked
    -0.66
     sustaining
    -0.66
    POSITIVE LOGITS
    76561
    1.03
    edu
    0.93
    iov
    0.92
    android
    0.91
    wordpress
    0.88
    park
    0.86
    com
    0.86
    kat
    0.85
    yahoo
    0.85
    services
    0.85
    Act Density 0.035%

    No Known Activations