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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "delete" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    meanor
    -0.77
    ocks
    -0.74
    atisk
    -0.71
     htons
    -0.70
     ICommand
    -0.70
    CharStream
    -0.65
    jsxFileName
    -0.64
    تيجة
    -0.64
     Roskov
    -0.63
    bkz
    -0.63
    POSITIVE LOGITS
    DeleteMapping
    1.60
     Delete
    1.37
     DELETE
    1.36
     delete
    1.32
    Delete
    1.26
     deletes
    1.25
    DELETE
    1.24
    delete
    1.23
     Deletes
    1.22
     deleting
    1.22
    Act Density 0.082%

    No Known Activations