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

    Neuronpedia

    INDEX
    Explanations

    phrases related to public criticism and social commentary

    oai_token-act-pair · gpt-3.5-turbo

    instances of criticism or discussion related to social norms and behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.74
    hiba
    -0.67
    staking
    -0.63
    soDeliveryDate
    -0.60
    çĶ°
    -0.55
    usa
    -0.55
    ilogy
    -0.53
    era
    -0.53
    ortium
    -0.53
    likely
    -0.52
    POSITIVE LOGITS
     anymore
    1.16
     nor
    0.87
     frivol
    0.84
     blindly
    0.80
     unnecessarily
    0.74
     crap
    0.68
     frivolous
    0.66
     anytime
    0.66
     anything
    0.64
     crappy
    0.62
    Act Density 1.501%

    No Known Activations