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

    Neuronpedia

    INDEX
    Explanations

    phrases related to explanations or methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azor
    -0.18
    enson
    -0.16
    çĽ
    -0.15
    arg
    -0.15
    bens
    -0.14
     Marilyn
    -0.14
    overview
    -0.14
    δει
    -0.14
    ajar
    -0.14
     Rough
    -0.14
    POSITIVE LOGITS
     Vys
    0.16
     NavParams
    0.15
    iola
    0.15
    aines
    0.15
    upal
    0.15
     seins
    0.15
    _deinit
    0.15
    okud
    0.14
    ering
    0.14
    tha
    0.14
    Act Density 0.001%

    No Known Activations