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

    Neuronpedia

    INDEX
    Explanations

    sections that begin with the word "About" or similar phrases indicating introductory information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ounced
    -0.14
    precated
    -0.14
    hab
    -0.14
    ÑĢÑĥÑĩ
    -0.14
    baz
    -0.14
    erate
    -0.14
    rid
    -0.13
    eri
    -0.13
    ız
    -0.13
     Hoe
    -0.13
    POSITIVE LOGITS
     Us
    0.32
    Us
    0.27
    -us
    0.22
    -face
    0.20
     us
    0.19
    IQUE
    0.17
     half
    0.16
     Yourself
    0.16
    urre
    0.16
    abela
    0.16
    Act Density 0.015%

    No Known Activations