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

    Neuronpedia

    INDEX
    Explanations

    sequences of steps or instructions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    idays
    -0.88
    atform
    -0.84
     Voices
    -0.74
    elaide
    -0.72
    oubted
    -0.71
     claimant
    -0.68
     Journals
    -0.68
    nesty
    -0.66
    ropolitan
    -0.66
    igration
    -0.65
    POSITIVE LOGITS
     routines
    1.21
     technique
    1.09
     tricks
    1.06
     routine
    1.03
     procedure
    1.02
     trick
    0.97
     instructions
    0.97
     manual
    0.97
     techniques
    0.95
     Instruct
    0.95
    Act Density 1.027%

    No Known Activations