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

    Neuronpedia

    INDEX
    Explanations

    social media platforms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "took to" indicating actions taken on social media platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Keeper
    -0.73
     Tsukuyomi
    -0.72
    soDeliveryDate
    -0.72
     fortun
    -0.69
    Mech
    -0.67
     Perse
    -0.66
    trained
    -0.65
    Offline
    -0.64
    Runner
    -0.64
    processing
    -0.63
    POSITIVE LOGITS
     criticize
    1.75
     denounce
    1.62
     clarify
    1.58
     reiterate
    1.55
     reassure
    1.53
     explain
    1.52
     refute
    1.51
     emphasize
    1.51
     condemn
    1.49
     accuse
    1.49
    Act Density 0.236%

    No Known Activations