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

    Neuronpedia

    INDEX
    Explanations

    mentions of the number "first" and ordinal or ranking-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omi
    -0.16
    åĭ
    -0.15
    Hang
    -0.15
    ledi
    -0.15
    ystate
    -0.15
     omas
    -0.15
    477
    -0.14
    phis
    -0.14
    /catalog
    -0.14
    edback
    -0.14
    POSITIVE LOGITS
    hari
    0.17
    æŁĦ
    0.17
    avel
    0.15
    ery
    0.15
    lein
    0.15
    akra
    0.14
    926
    0.14
    arian
    0.14
     rounding
    0.14
     Sanders
    0.14
    Act Density 0.020%

    No Known Activations