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

    Neuronpedia

    INDEX
    Explanations

    words related to the addition or signing of new elements or entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "of" indicating relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucci
    -0.79
    ength
    -0.77
     portrayal
    -0.69
    arat
    -0.68
    Merit
    -0.68
    é¾įåĸļ士
    -0.65
    acci
    -0.65
     depiction
    -0.63
    onge
    -0.63
    igue
    -0.63
    POSITIVE LOGITS
     fresh
    0.67
     hostilities
    0.66
     these
    0.64
    leased
    0.63
    ãĥĢ
    0.63
     Mart
    0.62
    xit
    0.61
     Innocent
    0.59
     Into
    0.57
     è£ıç
    0.57
    Act Density 0.172%

    No Known Activations