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

    Neuronpedia

    INDEX
    Explanations

    references to investigations or potential collusions involving Russia, particularly related to the 2016 US presidential election

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Russia and its involvement in US politics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dart
    -0.77
    dash
    -0.76
    Thom
    -0.74
    prototype
    -0.74
    Label
    -0.72
    }}}
    -0.71
    jj
    -0.70
    jc
    -0.69
    ulton
    -0.69
    draw
    -0.68
    POSITIVE LOGITS
     dossier
    0.91
     collusion
    0.89
     blackmail
    0.89
     meddling
    0.88
     infiltrated
    0.86
     interfered
    0.85
     disinformation
    0.84
     intelligence
    0.83
     invaded
    0.83
    afort
    0.82
    Act Density 0.034%

    No Known Activations