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

    Neuronpedia

    INDEX
    Explanations

    variables and technical terminology related to programming or technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rex
    -0.18
    umd
    -0.15
    reso
    -0.15
    ufs
    -0.15
    ottage
    -0.14
    /Common
    -0.14
    afari
    -0.14
    oppel
    -0.14
     frat
    -0.14
     kl
    -0.14
    POSITIVE LOGITS
    姫
    0.17
    æ²¢
    0.14
    erti
    0.14
    _dw
    0.14
    held
    0.14
    å«Į
    0.14
     hã
    0.13
    nis
    0.13
    achts
    0.13
    SAT
    0.13
    Act Density 0.025%

    No Known Activations