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

    Neuronpedia

    INDEX
    Explanations

    websites and domain names with high activations

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the domain suffix ".com"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Balt
    -0.68
     strengthening
    -0.64
     bruising
    -0.63
    laus
    -0.63
     restrained
    -0.63
     progress
    -0.63
     deepening
    -0.61
     chilly
    -0.61
     consequential
    -0.61
     saline
    -0.61
    POSITIVE LOGITS
     Ltd
    0.98
    pleted
    0.98
     LTD
    0.94
    psons
    0.91
    lisher
    0.88
    edia
    0.87
     LLC
    0.84
    /#
    0.83
    biz
    0.82
     homepage
    0.81
    Act Density 0.034%

    No Known Activations