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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "delete" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     htons
    -0.80
     AssemblyCulture
    -0.75
    jsxFileName
    -0.73
    meanor
    -0.73
     Roskov
    -0.72
    CharStream
    -0.70
    OrBuilder
    -0.70
     ICommand
    -0.69
    atisk
    -0.68
    ведено
    -0.65
    POSITIVE LOGITS
     Delete
    1.53
     DELETE
    1.46
     delete
    1.45
    Delete
    1.43
    DeleteMapping
    1.40
    delete
    1.39
     deleting
    1.38
     Deletes
    1.35
     deletes
    1.35
    DELETE
    1.33
    Act Density 0.052%

    No Known Activations