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

    Neuronpedia

    INDEX
    Explanations

    links for sharing content on various social media platforms

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sharing content on social media platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Trails
    -1.01
     Practices
    -0.94
     Paran
    -0.93
     Temper
    -0.92
     Amen
    -0.91
     Dietary
    -0.90
     Putting
    -0.89
     Beef
    -0.88
    Term
    -0.88
     Tape
    -0.88
    POSITIVE LOGITS
     agg
    0.98
     exhib
    0.87
     green
    0.83
     hesitate
    0.83
     medium
    0.82
     complain
    0.81
     miss
    0.80
     reserve
    0.80
     disarm
    0.78
     aven
    0.78
    Act Density 0.360%

    No Known Activations