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

    Neuronpedia

    INDEX
    Explanations

    phrases related to editing and modifying content

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "edit" in various contexts related to modification or configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipal
    -0.70
    phalt
    -0.68
    seys
    -0.67
    cent
    -0.67
     Ballistic
    -0.66
    gdala
    -0.66
     Ferry
    -0.65
    ayed
    -0.64
    nen
    -0.62
    iffe
    -0.62
    POSITIVE LOGITS
     edit
    1.20
     edits
    0.94
    edit
    0.87
     editing
    0.86
    ipedia
    0.81
    orship
    0.75
     Edit
    0.71
     spoiler
    0.70
    Edit
    0.69
    UTC
    0.68
    Act Density 0.013%

    No Known Activations