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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash

    specific chemical compounds and their safety information in the context of industrial use.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    i
    -0.09
     leur
    -0.08
    ir
    -0.07
     дисцип
    -0.07
     lingerie
    -0.07
     Adri
    -0.07
    lvl
    -0.07
    II
    -0.06
     Bir
    -0.06
     Burg
    -0.06
    POSITIVE LOGITS
     that
    0.14
     That
    0.13
     THAT
    0.11
    that
    0.11
     Because
    0.11
    That
    0.10
    -that
    0.10
    "That
    0.10
    “That
    0.10
     which
    0.09
    Act Density 0.284%

    No Known Activations