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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing collective or group associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following "of" in phrases

    np_acts-logits-general · gemini-2.0-flash

    numbers and groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dieux
    -0.65
     picioare
    -0.57
     témoins
    -0.57
    存于互联网档案馆
    -0.56
     peines
    -0.55
     chivalry
    -0.55
     esetén
    -0.55
     écl
    -0.55
     partea
    -0.55
     démission
    -0.55
    POSITIVE LOGITS
     seven
    0.83
     six
    0.81
     dozen
    0.78
    `,
    0.78
     four
    0.78
     eight
    0.76
     nine
    0.76
    %;
    0.72
     sorts
    0.72
     five
    0.71
    Act Density 0.298%

    No Known Activations