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

    Neuronpedia

    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     disreg
    -0.88
     scrat
    -0.88
     impra
    -0.83
     bosch
    -0.82
     embodi
    -0.81
     tupperware
    -0.80
     suscep
    -0.79
     snoopy
    -0.77
     lpg
    -0.77
     overcrow
    -0.76
    POSITIVE LOGITS
     alumínio
    0.61
    hermoso
    0.57
    ⓧ
    0.57
     BioLib
    0.56
    Dermott
    0.55
    acrylamide
    0.54
     Estudiantes
    0.53
    UserScript
    0.52
     Gallimard
    0.51
     Cataluña
    0.51
    Act Density 0.319%

    No Known Activations