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

    Neuronpedia

    INDEX
    Explanations

    numeric representations related to ratings and reviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nd
    -0.22
    ched
    -0.18
    ESCO
    -0.18
    ional
    -0.17
    ngr
    -0.17
    stag
    -0.16
     Hicks
    -0.16
    nt
    -0.16
    lest
    -0.15
    /is
    -0.15
    POSITIVE LOGITS
    -HT
    0.35
    -star
    0.26
    де
    0.23
    -Star
    0.21
    Thirty
    0.20
     borough
    0.19
    555
    0.18
    fold
    0.18
    .Qt
    0.17
    etto
    0.17
    Act Density 0.294%

    No Known Activations