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

    Neuronpedia

    INDEX
    Explanations

    words related to different locations and specific names, potentially geographical references

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     cryst
    -0.65
     Cornwall
    -0.64
    Fed
    -0.62
     Tempest
    -0.61
     Staples
    -0.61
     Adin
    -0.60
     poppy
    -0.60
    resp
    -0.60
     Hallow
    -0.59
    FACE
    -0.59
    POSITIVE LOGITS
    owski
    1.17
    iewicz
    1.13
    owsky
    1.02
    ovich
    0.97
    ovic
    0.95
    oglu
    0.94
    olor
    0.92
    lar
    0.91
    ova
    0.90
    anth
    0.90
    Act Density 0.043%

    No Known Activations