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

    Neuronpedia

    INDEX
    Explanations

    phrases related to deleting or removing content or information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "delete" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annis
    -0.96
     negotiators
    -0.73
    Building
    -0.71
    acs
    -0.68
    orsi
    -0.67
    gio
    -0.66
    ETF
    -0.66
    enegger
    -0.65
    NG
    -0.63
    verning
    -0.63
    POSITIVE LOGITS
     Delete
    0.92
     delet
    0.86
     delete
    0.82
     deleted
    0.81
    leted
    0.74
    abytes
    0.73
    utsche
    0.68
    itor
    0.67
     å¤
    0.65
     deleting
    0.65
    Act Density 0.027%

    No Known Activations