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

    Neuronpedia

    INDEX
    Explanations

    keywords related to information and communication such as "sent," "information," "available," and "reported."

    oai_token-act-pair · gpt-3.5-turbo

    words related to the dissemination and collection of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quit
    -0.77
    Interstitial
    -0.72
    wagen
    -0.71
    Anti
    -0.68
     externalToEVAOnly
    -0.67
    Madison
    -0.67
     mayors
    -0.66
     Zed
    -0.66
    ogun
    -0.63
    Death
    -0.63
    POSITIVE LOGITS
     glean
    1.11
     dossier
    0.92
     Steele
    0.86
    enhagen
    0.83
     gathered
    0.78
     collected
    0.75
     confidential
    0.73
    transfer
    0.72
     clipboard
    0.72
     databases
    0.71
    Act Density 0.388%

    No Known Activations