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

    Neuronpedia

    INDEX
    Explanations

    words related to changes or improvements in circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oor
    -0.20
    iske
    -0.17
    orida
    -0.16
     otherwise
    -0.16
    lt
    -0.15
    vang
    -0.14
    EO
    -0.14
     Shades
    -0.14
     triang
    -0.14
     buoy
    -0.14
    POSITIVE LOGITS
    dum
    0.16
    Ø¢Ùħ
    0.16
    ifton
    0.15
    خاÙĨÙĩ
    0.15
    erness
    0.15
    ellungen
    0.15
    -eslint
    0.15
    erable
    0.15
    .ObjectModel
    0.14
    gratis
    0.14
    Act Density 0.004%

    No Known Activations