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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to various fields of study or characteristics, particularly those with specific suffixes that convey quality or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    तम
    -0.17
    ORB
    -0.17
    olle
    -0.16
    aneously
    -0.16
     Voll
    -0.15
    ily
    -0.15
    862
    -0.15
    anou
    -0.15
    ably
    -0.14
    ively
    -0.14
    POSITIVE LOGITS
     speaking
    0.19
     Speaking
    0.19
    Speaking
    0.18
    adr
    0.17
    sound
    0.15
    /math
    0.15
    mph
    0.15
     sound
    0.14
    xx
    0.14
     savvy
    0.14
    Act Density 0.061%

    No Known Activations