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

    phrases that reference the concept of adding something, particularly in the context of value or contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     WATCHED
    -0.71
     Gram
    -0.70
     Zel
    -0.67
    NING
    -0.67
     Nets
    -0.66
     Zurich
    -0.64
     Reform
    -0.63
    ograms
    -0.63
    DEM
    -0.62
     writ
    -0.61
    POSITIVE LOGITS
    ictions
    1.12
    endum
    1.12
    itional
    1.04
    itionally
    1.03
    icted
    0.92
     insult
    0.91
    ition
    0.91
    itious
    0.90
    itions
    0.90
    itivity
    0.88
    Act Density 0.042%

    No Known Activations