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

    Neuronpedia

    INDEX
    Explanations

    words related to actions involving removal or deletion

    oai_token-act-pair · gpt-3.5-turbo

    words related to the act of removing or elimination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogi
    -0.76
    lance
    -0.67
    agon
    -0.67
     Lives
    -0.65
    ogly
    -0.64
    lain
    -0.64
     Rus
    -0.63
    typ
    -0.62
     Dreams
    -0.62
     Led
    -0.62
    POSITIVE LOGITS
     remove
    3.12
    Remove
    2.39
    remove
    2.37
     Remove
    2.28
     removes
    2.17
     removing
    2.12
     removed
    2.04
     removal
    1.97
     delete
    1.64
     Removal
    1.57
    Act Density 0.023%

    No Known Activations