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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inclusivity or collective belonging

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize collective experience or unity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bots
    -0.63
    kers
    -0.60
    nect
    -0.59
     Nerd
    -0.58
    cdn
    -0.57
    ULTS
    -0.56
     Featured
    -0.53
    Plex
    -0.53
    cers
    -0.52
     Minority
    -0.52
    POSITIVE LOGITS
    agher
    0.70
     else
    0.68
    upon
    0.63
     except
    0.63
    ocating
    0.62
    iance
    0.62
     -
    0.61
    ieu
    0.60
    ocation
    0.59
     --
    0.59
    Act Density 0.124%

    No Known Activations