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

    Neuronpedia

    INDEX
    Explanations

    frequency and mentions of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     büyü
    -0.61
     racines
    -0.58
    cierre
    -0.54
     permeability
    -0.54
    ◀
    -0.54
     formales
    -0.53
     Permeability
    -0.53
    EventEmitter
    -0.53
     Theory
    -0.52
     innamor
    -0.51
    POSITIVE LOGITS
    +#+#
    1.26
    ThroughAttribute
    1.03
    ViewFeatures
    0.94
    IntoConstraints
    0.89
    tableFuture
    0.88
     виправивши
    0.87
    vábbi
    0.86
    mtliche
    0.86
    Tikang
    0.81
    ]")]
    0.81
    Act Density 0.116%

    No Known Activations