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

    Neuronpedia

    INDEX
    Explanations

    symbols or characters that indicate formatting or special sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ãģ
    -0.15
     еÑij
    -0.14
     [âĢ¦]
    -0.14
     ‘
    -0.14
     Ib
    -0.14
    ALCHEMY
    -0.14
    ça
    -0.14
     cos
    -0.13
     «
    -0.13
     Télé
    -0.13
    POSITIVE LOGITS
     Luis
    0.29
     Nav
    0.22
    Nav
    0.20
    UIS
    0.20
    uis
    0.19
    LU
    0.19
    .lu
    0.19
    NAV
    0.19
     NAV
    0.19
     Navigation
    0.18
    Act Density 0.004%

    No Known Activations