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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the act of performing actions or being influenced by external sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agnar
    -0.16
    KeySpec
    -0.15
    ãģ¡ãĤĥãĤĵ
    -0.15
    IGHL
    -0.15
    IBUTE
    -0.15
    abay
    -0.14
    ãĥ¼ãĥķ
    -0.14
    CLUDING
    -0.14
    å¿Ļ
    -0.14
    amiliar
    -0.14
    POSITIVE LOGITS
     means
    0.32
     virtue
    0.29
    -products
    0.28
    products
    0.25
    /on
    0.24
     chance
    0.23
    laws
    0.23
     us
    0.22
    /to
    0.22
    rne
    0.21
    Act Density 0.314%

    No Known Activations