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

    Neuronpedia

    INDEX
    Explanations

    references or citations within text

    oai_token-act-pair · gpt-3.5-turbo

    citations of sources or reports in news articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ç¥ŀ
    -0.76
    itol
    -0.75
    btn
    -0.74
    emption
    -0.74
    illion
    -0.74
    ovation
    -0.69
    Synopsis
    -0.69
    ukong
    -0.69
     Congratulations
    -0.67
    pron
    -0.67
    POSITIVE LOGITS
     eyewitness
    1.70
     informants
    1.58
     witnesses
    1.50
     sources
    1.45
     interviews
    1.43
     testimonies
    1.33
     affidav
    1.25
     witness
    1.25
     insiders
    1.23
     unnamed
    1.22
    Act Density 0.334%

    No Known Activations