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

    Neuronpedia

    INDEX
    Explanations

    words related to industrial or organizational processes and actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of 'ization.'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     neighboring
    -0.71
     neighbors
    -0.67
     Rollins
    -0.67
     honored
    -0.67
    MORE
    -0.64
    Ľ
    -0.63
    avored
    -0.62
     traveling
    -0.61
     honorable
    -0.61
     longtime
    -0.59
    POSITIVE LOGITS
    isation
    4.43
    isations
    3.51
    ization
    2.99
    ised
    2.84
    izations
    2.79
    ising
    2.73
    isers
    2.27
    isable
    2.24
    ises
    2.10
    iser
    2.00
    Act Density 0.009%

    No Known Activations