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

    Neuronpedia

    INDEX
    Explanations

    references to academic institutions and legal terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥģãĥ¥
    -0.17
    hem
    -0.17
     Klo
    -0.16
    .setTo
    -0.16
    OTS
    -0.15
    echa
    -0.15
    CTS
    -0.15
    eros
    -0.14
    nts
    -0.14
    lue
    -0.14
    POSITIVE LOGITS
     Massachusetts
    0.41
     Boston
    0.41
    Boston
    0.38
     Celtics
    0.28
     MIT
    0.26
    /MIT
    0.24
     Harvard
    0.23
     Rhode
    0.20
    achusetts
    0.20
     Yankee
    0.19
    Act Density 0.193%

    No Known Activations