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

    Neuronpedia

    INDEX
    Explanations

    expressions of enjoyment or positive reception towards written content

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to enjoyment or appreciation of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fame
    -0.74
    soDeliveryDate
    -0.70
     authority
    -0.63
     legion
    -0.63
     blame
    -0.63
     believers
    -0.60
     sovere
    -0.59
     demons
    -0.57
     kings
    -0.57
     hypoc
    -0.57
    POSITIVE LOGITS
    iked
    1.00
     Flavoring
    0.83
     Below
    0.78
    EngineDebug
    0.77
    rupal
    0.75
     reading
    0.68
     Helpful
    0.68
    Comments
    0.67
    iled
    0.67
    Interested
    0.66
    Act Density 0.085%

    No Known Activations