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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations, particularly cities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.81
    tein
    -0.76
    yip
    -0.72
    achev
    -0.70
    manship
    -0.65
    kaya
    -0.65
    lift
    -0.65
    krit
    -0.64
    Downloadha
    -0.61
    POSE
    -0.58
    POSITIVE LOGITS
    oglu
    0.78
    igham
    0.78
    opolis
    0.75
     Blanc
    0.72
    adr
    0.70
    ante
    0.68
    ornia
    0.68
    ulas
    0.66
     dots
    0.66
     Sole
    0.65
    Act Density 0.156%

    No Known Activations