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

    Neuronpedia

    INDEX
    Explanations

    possessive forms of nouns, particularly in the context of ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahon
    -0.93
    selves
    -0.85
    rg
    -0.84
    remlin
    -0.84
    enhagen
    -0.81
    STER
    -0.79
    erest
    -0.79
    eller
    -0.79
    facts
    -0.76
    utral
    -0.76
    POSITIVE LOGITS
     Day
    0.93
     Syndrome
    0.88
     Mansion
    0.84
     Gate
    0.84
     Circle
    0.83
     Landing
    0.79
     Counsel
    0.79
     Medal
    0.79
     Creed
    0.78
     Reserve
    0.75
    Act Density 0.021%

    No Known Activations