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

    Neuronpedia

    INDEX
    Explanations

    language learning tools and platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tact
    -0.15
    ayne
    -0.15
    azor
    -0.15
     fr
    -0.15
    oha
    -0.15
     sph
    -0.14
     Kaiser
    -0.14
    arra
    -0.14
     DWC
    -0.14
    uffix
    -0.14
    POSITIVE LOGITS
    ijo
    0.18
    ombie
    0.18
    dech
    0.16
    ardown
    0.16
    nge
    0.15
    ansi
    0.14
    umo
    0.14
    ium
    0.14
     Prest
    0.14
    urm
    0.14
    Act Density 0.012%

    No Known Activations