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

    Neuronpedia

    INDEX
    Explanations

    words related to completing or finishing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.96
     PyTuple
    -0.79
    +#+#
    -0.78
     Krä
    -0.78
     grotte
    -0.77
     Vallarta
    -0.77
    pyr
    -0.77
     Mew
    -0.76
    qrstuvwxyz
    -0.76
    TagMode
    -0.75
    POSITIVE LOGITS
     Finish
    1.06
     FINISH
    1.04
    FINISH
    0.95
    Finish
    0.91
     finish
    0.89
    finish
    0.87
     finishes
    0.86
    FINISHED
    0.85
     finished
    0.83
     Finished
    0.83
    Act Density 0.069%

    No Known Activations