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

    Neuronpedia

    INDEX
    Explanations

    references to uncertainty or conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    س
    -0.18
    -s
    -0.18
    -S
    -0.18
    ãĤµ
    -0.17
    ¬¸
    -0.17
    _S
    -0.16
    ÂŃs
    -0.16
    arios
    -0.16
    _s
    -0.15
     D
    -0.15
    POSITIVE LOGITS
    T
    0.20
    -T
    0.20
    ãĤ¨
    0.19
    _E
    0.19
     E
    0.18
    -t
    0.18
    ÐŃ
    0.17
    E
    0.17
    ĺ
    0.17
    An
    0.17
    Act Density 0.115%

    No Known Activations