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

    Neuronpedia

    INDEX
    Explanations

    quantitative references, particularly the word "least" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ock
    -0.16
    ast
    -0.15
    ONLY
    -0.14
    oug
    -0.14
     Rosenstein
    -0.14
    bard
    -0.14
     apenas
    -0.13
     Yates
    -0.13
    alink
    -0.13
    osed
    -0.13
    POSITIVE LOGITS
    urret
    0.17
    ITUDE
    0.15
     Levi
    0.14
    sic
    0.14
    itude
    0.14
    weg
    0.14
    eguard
    0.14
    ashing
    0.14
     partial
    0.14
    serial
    0.14
    Act Density 0.022%

    No Known Activations