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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causation or reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĤа
    -0.16
    ¹
    -0.15
    ERSION
    -0.14
    коÑĤ
    -0.14
    erialize
    -0.14
    ấp
    -0.14
    ecd
    -0.14
    onical
    -0.14
    SELF
    -0.13
    mana
    -0.13
    POSITIVE LOGITS
     lack
    0.17
    age
    0.16
    éal
    0.15
    dup
    0.14
     Oswald
    0.14
    ληÏĤ
    0.14
    eof
    0.14
     Fletcher
    0.14
    lease
    0.13
    #__
    0.13
    Act Density 0.068%

    No Known Activations