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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement or transportation between different locations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Democr
    -0.76
     Mort
    -0.70
     Fine
    -0.66
     Examiner
    -0.66
     Stub
    -0.66
     FAT
    -0.66
     Panda
    -0.65
     Tasman
    -0.64
     Pony
    -0.64
     Cats
    -0.63
    POSITIVE LOGITS
    rogens
    1.09
    rogen
    1.04
    Against
    0.90
    against
    0.88
     without
    0.78
     Against
    0.78
    excluding
    0.77
     against
    0.76
    within
    0.76
    20439
    0.76
    Act Density 0.050%

    No Known Activations