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

    Neuronpedia

    INDEX
    Explanations

    mentions of actions related to deletion or removal

    oai_token-act-pair · gpt-3.5-turbo

    instances related to the action of deleting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annis
    -0.98
    gio
    -0.73
     negotiators
    -0.70
    acs
    -0.68
    Building
    -0.67
    enegger
    -0.67
    ebus
    -0.64
    asio
    -0.64
    ingham
    -0.64
    ETF
    -0.64
    POSITIVE LOGITS
     Delete
    0.92
     delet
    0.85
     delete
    0.80
     deleted
    0.75
    leted
    0.74
    ãĤ¯
    0.68
    abytes
    0.66
    ãĤ´
    0.65
    itor
    0.65
    orate
    0.65
    Act Density 0.026%

    No Known Activations