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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "delete" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     htons
    -0.78
    jsxFileName
    -0.77
    WarningLevel
    -0.74
    mirante
    -0.71
     AssemblyCulture
    -0.69
     settling
    -0.65
     Hock
    -0.64
    ynchrotron
    -0.64
    ведено
    -0.63
    ambito
    -0.62
    POSITIVE LOGITS
     delete
    2.23
    delete
    2.18
     Delete
    2.17
    Delete
    2.08
     DELETE
    1.94
     deleting
    1.91
    DELETE
    1.87
     deletes
    1.85
     Deletes
    1.73
     deleted
    1.72
    Act Density 0.024%

    No Known Activations