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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical connections or relationships

    oai_token-act-pair · gpt-3.5-turbo

    the frequency of the word "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parency
    -0.70
     boycot
    -0.69
    calling
    -0.66
     sponsored
    -0.65
    hur
    -0.64
    announced
    -0.63
    rio
    -0.62
    comments
    -0.62
     vetting
    -0.62
    åij
    -0.61
    POSITIVE LOGITS
    ggles
    1.12
    othy
    0.98
     accommodate
    0.96
     minimize
    0.95
     maximize
    0.92
     compensate
    0.91
     conserve
    0.90
     ensure
    0.87
     shore
    0.87
     avoid
    0.85
    Act Density 0.341%

    No Known Activations