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

    Neuronpedia

    INDEX
    Explanations

    the presence of the letter 'a' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vig
    -0.77
     investi
    -0.74
     indepen
    -0.74
     enthusi
    -0.72
     esper
    -0.72
    kti
    -0.71
     kari
    -0.70
     opis
    -0.69
     piment
    -0.68
     equili
    -0.68
    POSITIVE LOGITS
    A
    1.34
    getA
    1.26
     A
    1.16
    aA
    1.01
    a
    1.00
     a
    0.88
     syke
    0.86
    tableFuture
    0.85
     cervello
    0.85
     brancas
    0.85
    Act Density 0.368%

    No Known Activations