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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "subject" and its variations, indicating a focus on topics or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ushing
    -0.20
    ÑĨен
    -0.17
    ersh
    -0.16
    loe
    -0.15
    inking
    -0.15
    oma
    -0.15
    thon
    -0.15
    thers
    -0.15
    adies
    -0.14
    asmus
    -0.14
    POSITIVE LOGITS
    ively
    0.32
    ivity
    0.27
    ivism
    0.25
    matter
    0.25
    ivities
    0.24
     matter
    0.24
    ivist
    0.22
     Matter
    0.20
    ive
    0.18
    æĿIJ
    0.17
    Act Density 0.014%

    No Known Activations