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

    Neuronpedia

    INDEX
    Explanations

    phrases related to cylindrical objects or structures, specifically tubes

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of tubes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå
    -0.75
    å°Ĩ
    -0.75
     Lowry
    -0.72
    eting
    -0.70
    icago
    -0.70
    nee
    -0.69
    ufact
    -0.69
    giving
    -0.68
    raising
    -0.68
     Herb
    -0.68
    POSITIVE LOGITS
     tube
    1.05
     tubes
    0.93
    ulla
    0.79
     Tube
    0.78
    tube
    0.75
     tubing
    0.73
     tunnel
    0.72
     stret
    0.71
    anus
    0.70
     pus
    0.70
    Act Density 0.015%

    No Known Activations