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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "center."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ✭✭
    -0.55
    Autoritní
    -0.52
    жидан
    -0.52
    romyalgia
    -0.51
    °°
    -0.50
    expandindo
    -0.49
    glades
    -0.49
     Administrativna
    -0.47
    ingway
    -0.47
    loos
    -0.47
    POSITIVE LOGITS
     center
    2.27
     centre
    2.13
    center
    1.81
    centre
    1.76
     centers
    1.58
     centres
    1.49
     middle
    1.42
    中心
    1.35
     centro
    1.33
    centers
    1.32
    Act Density 0.084%

    No Known Activations