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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating outcomes or results of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inish
    -0.15
    eniable
    -0.15
    tras
    -0.14
    ching
    -0.14
    ¨
    -0.14
     gaat
    -0.14
    endra
    -0.13
    nev
    -0.13
    inja
    -0.13
     undesirable
    -0.13
    POSITIVE LOGITS
     être
    0.17
     essere
    0.16
    ุà¸Ķà¸Ĺ
    0.16
     be
    0.15
    ride
    0.15
     byÄĩ
    0.15
    DRV
    0.14
    agma
    0.14
    Utf
    0.14
    utzer
    0.14
    Act Density 0.027%

    No Known Activations