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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "We"

    oai_token-act-pair · gpt-3.5-turbo

    collective pronouns indicating group actions or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     UD
    -0.72
     gratification
    -0.67
     totality
    -0.67
     LSD
    -0.66
    cum
    -0.65
     quo
    -0.65
     otherwise
    -0.61
     srfAttach
    -0.61
     resting
    -0.59
     Wikipedia
    -0.57
    POSITIVE LOGITS
    ldon
    1.21
    bley
    1.18
    eks
    1.16
    ird
    1.12
    akening
    1.08
    bsite
    1.08
    alth
    1.07
    've
    1.07
    zbollah
    1.06
    're
    1.04
    Act Density 0.091%

    No Known Activations