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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "only" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.76
    $($
    -0.68
     zah
    -0.65
    Korn
    -0.64
     Verdi
    -0.64
     Davenport
    -0.63
     Schubert
    -0.63
    Vex
    -0.61
    िल्म
    -0.61
     Ather
    -0.61
    POSITIVE LOGITS
     only
    1.60
     Only
    1.37
     ONLY
    1.32
    ONLY
    1.32
    Only
    1.28
    only
    1.27
    Sólo
    1.13
     seulement
    1.12
    nly
    1.11
     лишь
    1.02
    Act Density 0.102%

    No Known Activations