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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and terms related to formulas and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lang
    -0.15
    orian
    -0.15
    Lang
    -0.14
     le
    -0.14
     rede
    -0.14
     lo
    -0.14
    .
    -0.14
     chi
    -0.13
     en
    -0.13
     et
    -0.13
    POSITIVE LOGITS
    _{
    0.30
    '_
    0.25
    _\
    0.24
    _X
    0.23
    _c
    0.22
    _T
    0.22
    _*
    0.22
    _a
    0.21
    _R
    0.21
    _I
    0.21
    Act Density 0.500%

    No Known Activations