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

    Neuronpedia

    INDEX
    Explanations

    geographical locations or directions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    thood
    -0.82
    rators
    -0.74
    Individual
    -0.74
    eat
    -0.73
    videos
    -0.72
     expr
    -0.70
    rix
    -0.70
    IQ
    -0.69
     suppose
    -0.68
     PROGRAM
    -0.68
    POSITIVE LOGITS
     footh
    1.39
     Strait
    1.24
     coastline
    1.21
     southwestern
    1.21
     shores
    1.20
     outskirts
    1.20
     northern
    1.19
     southern
    1.18
     southeastern
    1.16
     southwest
    1.16
    Act Density 0.264%

    No Known Activations