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

    Neuronpedia

    INDEX
    Explanations

    prepositions and phrases starting with 'ways in'

    oai_token-act-pair · gpt-3.5-turbo

    phrases that discuss methods or ways of doing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owship
    -0.61
     Demand
    -0.59
    ivity
    -0.59
     Constitutional
    -0.59
     appre
    -0.59
    ATTLE
    -0.59
    rities
    -0.59
    Day
    -0.58
     Sagan
    -0.58
    lux
    -0.58
    POSITIVE LOGITS
     approach
    0.73
    isSpecialOrderable
    0.70
    rez
    0.69
     conduit
    0.68
    soType
    0.65
    interstitial
    0.63
    hin
    0.63
    rison
    0.63
    reflect
    0.62
    rollers
    0.61
    Act Density 0.130%

    No Known Activations