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

    Neuronpedia

    INDEX
    Explanations

    words related to completion or finishing tasks

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.88
     Clyde
    -0.74
    شوند
    -0.73
     Yeon
    -0.73
    iastes
    -0.71
    RefNanny
    -0.70
    avax
    -0.69
    martre
    -0.69
     Orioles
    -0.68
     Chwiliwch
    -0.68
    POSITIVE LOGITS
     FINISH
    0.81
     Finish
    0.81
     finished
    0.80
     ​​
    0.79
    FINISH
    0.79
    FINISHED
    0.79
     unfinished
    0.77
    Finish
    0.77
     Finished
    0.77
    Finished
    0.77
    Act Density 0.011%

    No Known Activations