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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases conveying commands or requests

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

    common verb phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intervening
    -0.40
    เนื้อ
    -0.39
    Доб
    -0.38
     prá
    -0.37
     veuillez
    -0.36
     rodillas
    -0.35
     revelou
    -0.35
     colgantes
    -0.34
    cantidad
    -0.34
    หน่อย
    -0.34
    POSITIVE LOGITS
     kaarangay
    0.61
    jsonwebtoken
    0.57
    IUrlHelper
    0.56
    انيف
    0.56
    ddots
    0.54
     Infórmanos
    0.52
     Roskov
    0.49
    GOTREF
    0.46
     дописавши
    0.45
    ?";
    0.45
    Act Density 0.041%

    No Known Activations