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

    Neuronpedia

    INDEX
    Explanations

    references to the Paris Agreement

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Paris."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ITH
    -0.85
    ramid
    -0.84
    uilt
    -0.77
    regor
    -0.76
    ownt
    -0.75
    ithing
    -0.74
    avorite
    -0.74
    estern
    -0.72
    arijuana
    -0.70
    ictionary
    -0.70
    POSITIVE LOGITS
     Hilton
    1.13
    ienne
    1.01
    furt
    0.94
     Mé
    0.88
     Attacks
    0.80
    ian
    0.78
    mouth
    0.77
    iens
    0.77
    etta
    0.76
     Gas
    0.76
    Act Density 0.017%

    No Known Activations