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

    Neuronpedia

    INDEX
    Explanations

    phrases related to addition or increase

    oai_token-act-pair · gpt-3.5-turbo

    terms related to increasing or contributing to a quantity or situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NING
    -0.69
    yah
    -0.65
    grim
    -0.64
     Zel
    -0.64
    Bey
    -0.63
    etary
    -0.61
    bin
    -0.60
    debian
    -0.60
    ARE
    -0.60
    scar
    -0.59
    POSITIVE LOGITS
    endum
    1.19
     insult
    1.05
    ictions
    1.04
    itional
    1.02
    itionally
    0.96
    ition
    0.93
    itivity
    0.89
    itions
    0.87
     thereto
    0.86
    itive
    0.85
    Act Density 0.067%

    No Known Activations