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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize the concept of "one thing" or commonality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    229
    -0.14
    ound
    -0.14
    gs
    -0.14
     Grade
    -0.14
    erro
    -0.14
    ouri
    -0.14
    erb
    -0.13
    Ñģо
    -0.13
     Haut
    -0.13
    ign
    -0.13
    POSITIVE LOGITS
    psc
    0.17
     constants
    0.16
     constant
    0.15
    rowave
    0.15
     Constant
    0.14
    ltra
    0.14
    kea
    0.14
    ìĬ¬
    0.14
    rame
    0.14
     íĻķìĭ¤
    0.14
    Act Density 0.048%

    No Known Activations