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

    Neuronpedia

    INDEX
    Explanations

    phrases related to adding or including something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "add."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lived
    -0.69
     Frie
    -0.68
    emies
    -0.67
    ariat
    -0.67
     COURT
    -0.66
    vez
    -0.65
    guided
    -0.65
     Veil
    -0.64
    cedented
    -0.61
    handled
    -0.61
    POSITIVE LOGITS
     add
    3.30
    Add
    2.10
     Add
    2.06
     adds
    1.95
     ADD
    1.84
     adding
    1.76
     added
    1.75
    add
    1.72
     additions
    1.60
     addon
    1.46
    Act Density 0.018%

    No Known Activations