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

    Neuronpedia

    INDEX
    Explanations

    phrases related to competition and performance improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gons
    -0.18
    asz
    -0.16
    uros
    -0.16
    udes
    -0.15
    tones
    -0.15
    MLS
    -0.14
    |r
    -0.14
    ragen
    -0.14
    elves
    -0.14
    cts
    -0.14
    POSITIVE LOGITS
     my
    0.14
     Splash
    0.14
     height
    0.14
    jÃŃ
    0.13
     bal
    0.13
    heck
    0.13
     mie
    0.13
     Mori
    0.13
    VECTOR
    0.13
    Ł
    0.13
    Act Density 0.002%

    No Known Activations