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

    Neuronpedia

    INDEX
    Explanations

    locations or specific events mentioned in passages

    oai_token-act-pair · gpt-3.5-turbo

    references to community engagement or events related to societal discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obyl
    -0.87
    ondon
    -0.73
    alys
    -0.69
    ãĥİ
    -0.67
    icidal
    -0.64
    dq
    -0.63
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.63
    '/
    -0.63
    seless
    -0.62
    £
    -0.62
    POSITIVE LOGITS
     HuffPost
    1.13
     reporters
    1.11
     Politico
    1.11
     POLITICO
    1.10
     BuzzFeed
    1.02
     his
    1.01
     excerpts
    1.00
     attendees
    0.96
     aides
    0.95
     commenters
    0.95
    Act Density 0.449%

    No Known Activations