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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causation or attribution

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carbuncle
    -0.69
    rooms
    -0.68
    talk
    -0.66
    bugs
    -0.65
    iries
    -0.65
     benches
    -0.65
    cgi
    -0.64
    options
    -0.63
     gloves
    -0.62
     needle
    -0.62
    POSITIVE LOGITS
     solely
    0.75
    ioned
    0.75
     disproportionately
    0.71
    itant
    0.69
     directly
    0.69
     squarely
    0.68
    в
    0.68
     principally
    0.67
     chiefly
    0.67
    SourceFile
    0.66
    Act Density 0.120%

    No Known Activations