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

    Neuronpedia

    INDEX
    Explanations

    technical or formal terms used in government, politics, and business

    oai_token-act-pair · gpt-3.5-turbo

    terms related to organization, teamwork, and structured activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uden
    -0.72
    ossier
    -0.69
    ccording
    -0.68
    uckland
    -0.68
    cale
    -0.67
    ettings
    -0.65
     destro
    -0.65
    roma
    -0.64
    akening
    -0.64
    emale
    -0.63
    POSITIVE LOGITS
    ishly
    0.89
    lessly
    0.84
    ically
    0.83
    ually
    0.82
    wise
    0.76
    arily
    0.76
    loads
    0.76
    ably
    0.74
    atively
    0.70
    breakers
    0.69
    Act Density 0.764%

    No Known Activations