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

    Neuronpedia

    INDEX
    Explanations

    phrases related to knowledge and expertise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑģÑĤÑİ
    -0.18
    amina
    -0.16
    SSERT
    -0.15
    zimmer
    -0.15
    gte
    -0.15
    lectic
    -0.15
    conte
    -0.15
    coli
    -0.14
    /rss
    -0.14
    toi
    -0.14
    POSITIVE LOGITS
    able
    0.25
    ingly
    0.23
    ledge
    0.23
    ably
    0.20
    ledged
    0.20
    les
    0.19
    edges
    0.18
    lege
    0.17
    edge
    0.17
    ABLE
    0.17
    Act Density 0.021%

    No Known Activations