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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical structures such as bridges

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    arily
    -0.81
    matically
    -0.71
    atically
    -0.67
    psy
    -0.67
    nesota
    -0.64
    ij士
    -0.63
    edition
    -0.63
    ccording
    -0.63
    iaries
    -0.63
    resy
    -0.63
    POSITIVE LOGITS
     Strait
    0.95
    port
    0.95
    roads
    0.91
    bridge
    0.85
     bridge
    0.83
     Bridges
    0.83
    yard
    0.83
     bridges
    0.81
    layer
    0.81
     connecting
    0.81
    Act Density 0.028%

    No Known Activations