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

    Neuronpedia

    INDEX
    Explanations

    references to physical structures such as bridges

    oai_token-act-pair · gpt-3.5-turbo

    mentions of bridges in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaries
    -0.66
    resy
    -0.64
    tical
    -0.64
    sat
    -0.61
    ever
    -0.60
    ::::::::
    -0.60
    edition
    -0.60
    soever
    -0.58
    Reporting
    -0.57
    aneously
    -0.57
    POSITIVE LOGITS
     bridge
    1.28
    bridge
    1.21
     bridges
    1.17
    wright
    0.98
    Bridge
    0.97
     Bridges
    0.97
     Bridge
    0.89
    roads
    0.84
     Strait
    0.81
    lift
    0.80
    Act Density 0.007%

    No Known Activations