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

    Neuronpedia

    INDEX
    Explanations

    words with a hyphen or dash in them

    oai_token-act-pair · gpt-3.5-turbo

    negative expressions or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izabeth
    -0.76
     Confederation
    -0.64
     Kom
    -0.62
     Chambers
    -0.60
     maturity
    -0.59
     fine
    -0.57
     Finnish
    -0.57
     Observatory
    -0.56
     LW
    -0.56
     welcomed
    -0.55
    POSITIVE LOGITS
    lang
    0.93
    net
    0.88
    tech
    0.85
    strings
    0.84
    laden
    0.84
    sylvania
    0.83
    cit
    0.82
    politics
    0.81
    duct
    0.81
    site
    0.81
    Act Density 0.111%

    No Known Activations