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

    instances of additive language or phrases indicating accumulation or addition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĸ¬
    -0.73
    externalActionCode
    -0.71
    Consumer
    -0.68
     resemb
    -0.68
    ãĥīãĥ©ãĤ´ãĥ³
    -0.67
    ··
    -0.64
     exha
    -0.64
    COLOR
    -0.64
    APH
    -0.62
    NING
    -0.62
    POSITIVE LOGITS
    icted
    1.28
    itional
    1.23
    itionally
    1.19
    iction
    1.17
    resses
    1.09
    icts
    1.07
    ressed
    1.05
    ictive
    1.05
    ition
    1.05
    ened
    1.03
    Act Density 0.013%

    No Known Activations