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

    Neuronpedia

    INDEX
    Explanations

    phrases related to editing text or documents

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "edit" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ptoms
    -0.70
    phal
    -0.68
    FE
    -0.67
    ramid
    -0.66
    quartered
    -0.66
    nergy
    -0.65
    gdala
    -0.64
    hood
    -0.64
    pir
    -0.63
    NetMessage
    -0.61
    POSITIVE LOGITS
     edit
    1.08
     edits
    1.07
     editing
    0.97
    edit
    0.87
    orship
    0.80
     summ
    0.78
    ipedia
    0.73
     Delete
    0.71
    Edit
    0.71
    arro
    0.71
    Act Density 0.015%

    No Known Activations