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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by geographical locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ratulations
    -0.83
    rils
    -0.81
    faced
    -0.80
    trump
    -0.74
    potion
    -0.74
    lethal
    -0.69
     inval
    -0.68
    few
    -0.67
    tops
    -0.66
    needed
    -0.66
    POSITIVE LOGITS
     afar
    1.37
     abroad
    1.06
     whom
    0.96
     whence
    0.87
     Albania
    0.87
     Generation
    0.85
     across
    0.84
     Denmark
    0.83
     Latvia
    0.81
     Uganda
    0.81
    Act Density 0.138%

    No Known Activations