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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "railroad."

    oai_token-act-pair · gpt-3.5-turbo

    references to railroads and transportation-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alysed
    -0.89
    =-=-=-=-=-=-=-=-
    -0.85
     Whilst
    -0.79
    forth
    -0.77
    Firstly
    -0.77
    adem
    -0.76
    ffield
    -0.73
     Firstly
    -0.72
     analyse
    -0.72
    ising
    -0.72
    POSITIVE LOGITS
     Sie
    0.72
     VIDEOS
    0.71
     Russo
    0.71
     Swanson
    0.70
     Northwestern
    0.70
    sburgh
    0.70
     Mellon
    0.69
    MENTS
    0.66
    DAQ
    0.66
     leveled
    0.62
    Act Density 0.073%

    No Known Activations