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

    Neuronpedia

    INDEX
    Explanations

    phrases related to restrictions and regulations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swick
    -0.17
    acre
    -0.17
    igm
    -0.15
    atoria
    -0.14
    eyin
    -0.14
     teaser
    -0.14
    odes
    -0.14
    riel
    -0.14
    agger
    -0.14
    nf
    -0.14
    POSITIVE LOGITS
    izza
    0.17
    loh
    0.16
    hazi
    0.15
    fcc
    0.15
    ture
    0.14
     Suzanne
    0.14
    обÑĭ
    0.14
    hardt
    0.14
    hausen
    0.14
    ãĥĥãĥĦ
    0.14
    Act Density 0.391%

    No Known Activations