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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols or operations related to equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.18
    id
    -0.18
    ↵
    -0.18
     heck
    -0.18
     the
    -0.17
     a
    -0.17
     anything
    -0.16
    sto
    -0.16
    "
    -0.15
    icc
    -0.15
    POSITIVE LOGITS
    linger
    0.16
    eman
    0.16
    ведиÑĤе
    0.15
    _".$
    0.15
    obe
    0.15
    WITHOUT
    0.15
    owed
    0.15
     адже
    0.15
    AndFeel
    0.14
     вед
    0.14
    Act Density 0.114%

    No Known Activations