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

    Neuronpedia

    INDEX
    Explanations

    phrases related to impactful influencers or significant causes

    oai_token-act-pair · gpt-3.5-turbo

    references to causes and driving forces behind events or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancies
    -0.82
    oshenko
    -0.74
     gust
    -0.73
    ided
    -0.73
    arent
    -0.72
    lys
    -0.72
    uci
    -0.68
    hiba
    -0.67
    conserv
    -0.66
    agate
    -0.66
    POSITIVE LOGITS
     Prev
    0.70
     attracting
    0.70
    ducers
    0.68
    ãĥĸ
    0.66
    代
    0.64
     extraord
    0.64
    ]=
    0.62
     artery
    0.61
     amongst
    0.61
     attraction
    0.60
    Act Density 0.370%

    No Known Activations