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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods and semicolons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    оÑĢалÑĮ
    -0.17
    *)_
    -0.16
     Twitch
    -0.15
    anyahu
    -0.15
     ourselves
    -0.13
    ally
    -0.13
    mailer
    -0.13
    artial
    -0.13
     atmos
    -0.13
    Agent
    -0.13
    POSITIVE LOGITS
     last
    0.17
     he
    0.17
     earlier
    0.16
     Lag
    0.15
    verte
    0.15
    affen
    0.15
     hey
    0.14
    ADVERTISEMENT
    0.14
    ervo
    0.14
    ulfilled
    0.14
    Act Density 0.084%

    No Known Activations