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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to safety and regulatory compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ful
    -0.17
     of
    -0.14
    вад
    -0.14
    holm
    -0.14
    arp
    -0.14
    iteral
    -0.14
     McN
    -0.14
    erli
    -0.14
    ucher
    -0.14
     Weaver
    -0.13
    POSITIVE LOGITS
    687
    0.17
    edBy
    0.15
    cci
    0.15
    673
    0.15
    ulaire
    0.14
    лаÑĤ
    0.14
    630
    0.14
    atik
    0.14
    ynes
    0.14
    948
    0.13
    Act Density 0.844%

    No Known Activations