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

    Neuronpedia

    INDEX
    Explanations

    repetitive use of the word “one” in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.58
    verwijspagina
    -0.58
    Παραπομπές
    -0.57
     препратки
    -0.57
     estimés
    -0.54
    )&
    -0.54
     IVA
    -0.53
     елның
    -0.53
    Biographie
    -0.53
    ]&
    -0.52
    POSITIVE LOGITS
    ⓧ
    0.61
    LookAnd
    0.58
    kriegs
    0.56
    Mga
    0.55
    Personendaten
    0.55
    FromArray
    0.55
    spaceBetween
    0.55
     one
    0.54
     ours
    0.53
    airbnb
    0.53
    Act Density 0.084%

    No Known Activations