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

    Neuronpedia

    INDEX
    Explanations

    phrases related to nuclear weapons, international relations, and political figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     pymysql
    -0.86
     rempla
    -0.86
     amitié
    -0.85
     légiti
    -0.85
     illustre
    -0.85
     vété
    -0.84
     exé
    -0.84
     prétend
    -0.83
     sappi
    -0.83
     recueil
    -0.82
    POSITIVE LOGITS
     there
    0.72
     it
    0.65
     we
    0.63
     etc
    0.60
    there
    0.59
     they
    0.59
     this
    0.56
     you
    0.56
     respectively
    0.53
     these
    0.52
    Act Density 0.393%

    No Known Activations