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
    -0.86
    ramid
    -0.82
    uilt
    -0.76
    estern
    -0.75
    pta
    -0.74
    ownt
    -0.74
    atcher
    -0.71
    avorite
    -0.71
    isSpecialOrderable
    -0.70
    regor
    -0.70
    POSITIVE LOGITS
     Hilton
    1.12
    ienne
    1.00
    furt
    0.91
    ians
    0.88
     Mé
    0.88
    ian
    0.86
    agne
    0.79
     Gas
    0.79
    iens
    0.77
    etta
    0.76
    Act Density 0.023%

    No Known Activations