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

    Neuronpedia

    INDEX
    Explanations

    references to measurements and statistics related to production or performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    extent
    -0.16
    agara
    -0.15
     sheer
    -0.15
     extent
    -0.15
    uma
    -0.15
    Extent
    -0.14
    ditor
    -0.14
    pearance
    -0.14
    jev
    -0.14
    faf
    -0.13
    POSITIVE LOGITS
    stood
    0.19
     Vulcan
    0.16
    tones
    0.15
    rupted
    0.15
    held
    0.14
     Vir
    0.14
     certainty
    0.14
    Ñĥжд
    0.14
    tin
    0.13
    ãģĻãĤĮãģ°
    0.13
    Act Density 0.672%

    No Known Activations