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

    Neuronpedia

    INDEX
    Explanations

    web URLs

    oai_token-act-pair · gpt-3.5-turbo

    the presence of URLs or web addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     grounding
    -0.77
     taxi
    -0.74
     cruise
    -0.72
     overlooked
    -0.72
     uphill
    -0.70
     conclud
    -0.69
     shaving
    -0.69
     looting
    -0.68
     taxis
    -0.68
     underestimated
    -0.67
    POSITIVE LOGITS
    com
    1.40
    blogspot
    1.22
    edu
    1.21
    cdn
    1.19
    org
    1.18
    gov
    1.14
    net
    1.11
    info
    1.11
    wordpress
    1.10
    yahoo
    1.10
    Act Density 0.092%

    No Known Activations