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

    Neuronpedia

    INDEX
    Explanations

    key information related to political and social events, especially conflicts and diplomatic talks

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     hairc
    -1.36
     swarovski
    -1.26
     scrat
    -1.18
     encomp
    -1.15
     embodi
    -1.15
     ecru
    -1.15
     apprehen
    -1.14
     cushi
    -1.13
     affor
    -1.12
     increa
    -1.10
    POSITIVE LOGITS
     spoke
    0.60
    EndInit
    0.59
    ]})
    0.59
    Географиясе
    0.58
     announced
    0.56
    Jereo
    0.56
    BeginInit
    0.56
     addressed
    0.55
     }],
    0.52
     speech
    0.52
    Act Density 0.435%

    No Known Activations