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

    Neuronpedia

    INDEX
    Explanations

    occurrences and variations of the word "this."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Marchand
    -0.61
     propOrder
    -0.60
    NameInMap
    -0.59
    ци
    -0.56
    casecmp
    -0.56
    )))
    -0.56
    )))
    -0.55
    带
    -0.55
     препратки
    -0.55
    Ciri
    -0.53
    POSITIVE LOGITS
    ConstraintMaker
    0.93
    CloseOperation
    0.83
     at
    0.80
     At
    0.76
    IntoConstraints
    0.72
    At
    0.71
     vantage
    0.71
     createdAt
    0.66
     least
    0.65
     تكبرها
    0.65
    Act Density 0.158%

    No Known Activations