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

    Neuronpedia

    INDEX
    Explanations

    collective pronouns and phrases indicating shared experience or knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oksen
    -0.15
    esti
    -0.15
    arine
    -0.15
    quia
    -0.15
    avia
    -0.14
    окон
    -0.14
    ucceeded
    -0.14
    roid
    -0.14
    \xaa
    -0.13
    lia
    -0.13
    POSITIVE LOGITS
     meet
    0.25
     witness
    0.24
     follows
    0.22
     follow
    0.21
     meeting
    0.21
     accompany
    0.21
    Meet
    0.21
     priv
    0.20
     learn
    0.20
     accompanies
    0.20
    Act Density 0.038%

    No Known Activations