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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and formulae

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (
    -0.27
    -ish
    -0.18
    (?:
    -0.14
    åIJ§
    -0.14
    ↵
    -0.14
    \
    -0.14
     Phong
    -0.14
    ing
    -0.14
     gam
    -0.14
    @brief
    -0.13
    POSITIVE LOGITS
    $↵
    0.20
    åĨĬ
    0.18
    $$$
    0.17
    ?$
    0.17
    oment
    0.16
    /INFO
    0.15
    .scalablytyped
    0.15
     $↵
    0.15
    (!_
    0.15
    èĽĽ
    0.15
    Act Density 0.077%

    No Known Activations