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

    Neuronpedia

    INDEX
    Explanations

    phrases related to official or legal documents

    oai_token-act-pair · gpt-3.5-turbo

    references to investigative documents or cases involving reputational allegations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jc
    -0.80
    rh
    -0.77
    ahime
    -0.74
    erd
    -0.73
    aird
    -0.72
    arij
    -0.71
    rm
    -0.70
    alone
    -0.69
     Portug
    -0.69
     Glob
    -0.69
    POSITIVE LOGITS
     dossier
    1.59
     Steele
    1.27
    ossier
    0.99
     mole
    0.82
     tro
    0.75
     sightings
    0.74
     memos
    0.73
     doping
    0.73
    agher
    0.72
     heaviest
    0.70
    Act Density 0.018%

    No Known Activations