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

    Neuronpedia

    INDEX
    Explanations

    phrases mentioning addition or contribution to something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a contribution or addition to a situation or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neys
    -0.75
    llan
    -0.72
    pires
    -0.66
    soever
    -0.65
    starter
    -0.65
    cius
    -0.64
    ocene
    -0.64
    anners
    -0.61
    hunter
    -0.59
    ologue
    -0.59
    POSITIVE LOGITS
    effic
    0.79
     frustration
    0.71
    itiveness
    0.69
     richness
    0.68
     belie
    0.68
    conserv
    0.67
     tremend
    0.66
     excess
    0.66
    Increases
    0.66
    staking
    0.65
    Act Density 0.063%

    No Known Activations