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

    Neuronpedia

    INDEX
    Explanations

    phrases related to informational disclaimers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     equ
    -0.15
    _Impl
    -0.14
    irates
    -0.14
    ascal
    -0.14
    issen
    -0.14
    ॰
    -0.14
    illes
    -0.14
     shut
    -0.13
     ind
    -0.13
    Collapse
    -0.13
    POSITIVE LOGITS
    thew
    0.19
    opia
    0.17
     rall
    0.16
    geç
    0.16
    mun
    0.15
     purposes
    0.15
    ındır
    0.15
     Mun
    0.15
    iliz
    0.15
    çĶļ
    0.15
    Act Density 0.029%

    No Known Activations