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

    Neuronpedia

    INDEX
    Explanations

    references to small, explosive devices or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arde
    -0.18
    alias
    -0.18
     alias
    -0.17
    rub
    -0.16
    775
    -0.15
    andas
    -0.14
     mess
    -0.14
    arity
    -0.14
    no
    -0.14
    enne
    -0.14
    POSITIVE LOGITS
     (<
    0.21
     ($.
    0.17
    ãĥĥãĥģ
    0.16
    )prepare
    0.16
    /small
    0.16
    emailer
    0.15
     olsa
    0.15
    /tiny
    0.15
    обов
    0.15
    ableObject
    0.14
    Act Density 0.458%

    No Known Activations